Daily Papers

Test-time scaling for large language models (LLMs) can involve generating multiple candidate solutions for selection or revising an earlier attempt. To guide selection and revision, we need a verifier that can estimate candidate correctness and provide evidence of failure. In competitive programming, however, official judging systems provide authoritative verdicts under finite submission budgets, without revealing failure explanations or failing inputs. To provide informative feedback without consuming official submissions, we formulate a task in which a model judges and diagnoses a candidate program using only the problem statement and source code, with generated counterexamples serving as checkable evidence. To evaluate this task, we build USACO-JUDGE from the USACO 2026 contests, using accepted and unaccepted programs written by human experts and multiple LLMs. We then train ARBITER, a 35B mixture-of-experts (MoE) agentic verifier, with reinforcement learning in a generic execution sandbox. Training raises counterexample success on incorrect programs from 40.61% to 62.67% and mean binary verdict accuracy on USACO-JUDGE from 71.41% to 87.41%, approaching frontier verification performance. Beyond verification, ARBITER outperforms baselines in both code selection and refinement. In an IOI 2026 case study, ARBITER-guided refinement raises GPT-OSS-120B's expected score above the gold-medal threshold under the official submission limit.

Binary classification involves predicting the label of an instance based on whether the model score for the positive class exceeds a threshold chosen based on the application requirements (e.g., maximizing recall for a precision bound). However, model scores are often not aligned with the true positivity rate. This is especially true when the training involves a differential sampling across classes or there is distributional drift between train and test settings. In this paper, we provide theoretical analysis and empirical evidence of the dependence of model score estimation bias on both uncertainty and score itself. Further, we formulate the decision boundary selection in terms of both model score and uncertainty, prove that it is NP-hard, and present algorithms based on dynamic programming and isotonic regression. Evaluation of the proposed algorithms on three real-world datasets yield 25%-40% gain in recall at high precision bounds over the traditional approach of using model score alone, highlighting the benefits of leveraging uncertainty.

We present a new approach for mitigating unfairness in learned classifiers. In particular, we focus on binary classification tasks over individuals from two populations, where, as our criterion for fairness, we wish to achieve similar false positive rates in both populations, and similar false negative rates in both populations. As a proof of concept, we implement our approach and empirically evaluate its ability to achieve both fairness and accuracy, using datasets from the fields of criminal risk assessment, credit, lending, and college admissions.

System One models output calibrated probabilities over typed answers such as categorical choices, ordinal levels, or binary outcomes, via a non-generative interface. Software can act on these probabilities through thresholds, cost-weighted choices, and escalation rules. Consequently, if these probabilities are miscalibrated or wording-sensitive, the software ma take unintended actions leaving human operators with no textual rationale to inspect. Current evaluations largely report accuracy and calibration on public classification datasets without a clear reference. We present TypedBench, a benchmark for typed decision models like Jev built from seven policy-labelled generators and nine evaluation suites. We report accuracy as median and range across paraphrases, and calibration error relative to the finite-sample noise floor of a matched, perfectly calibrated predictor. We assess probability quality through selective prediction, ordinal proper scoring rules, and realised cost under asymmetric cost matrices. We evaluate a hosted model, an open encoder, and a family of open decoders spanning 0.8B-9B parameters on identical items. The hosted model follows the stated policy but is wording-sensitive and systematically underconfident; under asymmetric costs, using its probabilities can be worse than taking its top answer. Decoders route exactly and are slow as options or questions are added. The decoder is least accurate on policy questions and degrades with more options. Overall, typed decision models must be evaluated jointly on policy adherence, wording robustness, probability quality, and induced decision outcomes.

In a legal system, judgment consistency is regarded as one of the most important manifestations of fairness. However, due to the complexity of factual elements that impact sentencing in real-world scenarios, few works have been done on quantitatively measuring judgment consistency towards real-world data. In this paper, we propose an evaluation metric for judgment inconsistency, Legal Inconsistency Coefficient (LInCo), which aims to evaluate inconsistency between data groups divided by specific features (e.g., gender, region, race). We propose to simulate judges from different groups with legal judgment prediction (LJP) models and measure the judicial inconsistency with the disagreement of the judgment results given by LJP models trained on different groups. Experimental results on the synthetic data verify the effectiveness of LInCo. We further employ LInCo to explore the inconsistency in real cases and come to the following observations: (1) Both regional and gender inconsistency exist in the legal system, but gender inconsistency is much less than regional inconsistency; (2) The level of regional inconsistency varies little across different time periods; (3) In general, judicial inconsistency is negatively correlated with the severity of the criminal charges. Besides, we use LInCo to evaluate the performance of several de-bias methods, such as adversarial learning, and find that these mechanisms can effectively help LJP models to avoid suffering from data bias.

Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph prompt. Sampling reduces this cost, but small balanced subsets change unweighted precision and F1. We introduce AMLworld-Compact, an evaluation set that retains every illicit test transaction and samples benign transactions from supervised-score strata. Its HT-Coreset protocol reduces evaluation targets by 271x and 611x on HI-Small and LI-Small. Horvitz-Thompson weights give unbiased full-test confusion-count estimates for fixed predictions; recall is exact, while precision and F1 are ratio estimates. In a held-out study using Graph Feature Preprocessor (GFP) features, one boosted-tree family defines strata for evaluating the other over 500 draws per configuration. At the released sizes, F1 RMSE is 0.00-2.58 percentage points versus 4.44-7.41 for uniform sampling with HT weights; conservative intervals remain broad. Under the evaluated graph prompts, seven open-weight LLMs have weighted precision near the predict-all-illicit baseline. In an outcome-stratified audit of 1,000 HI-Small few-shot outputs from one run per model, lexical checks pass for 84.5% of correct and 56.2% of incorrect binary verdicts, so these markers do not establish correctness. We release the evaluation sets, construction code, and audit tools at https://huggingface.co/datasets/typhoon-ai/AMLworldCompactEval and https://github.com/nat-nischw/AMLworld-Compact.

E-commerce platforms have begun recruiting crowdsourced jurors to adjudicate massive volumes of transaction disputes. Unlike formal legal judgment, E-commerce dispute verdicts require grounding pivotal clues from redundant, multi-round, multimodal evidence and making decisions under flexible platform-specific conventions. These characteristics render existing methods insufficient for this scenario. To bridge this gap, we introduce a pioneering task, E-commerce Dispute Verdicts (EDV), and present VerdictBench, a multimodal benchmark comprising 6,000 real-world cases designed to reflect crowdsourced jury decisions. Building upon this, we propose CyberJurors, a multi-agent framework to clarify the dispute logic and regulate the verdict process. At the individual level, Individual Verdict Chain-of-Thought decomposes the EDV task into four structured reasoning stages, enabling fine-grained clue perception and clarifying causal logic between pivotal clues and the dispute focus. At the collective level, Jury Consensus Verdict simulates multi-round discussion and voting among jurors, while incorporating verdict precedents to mitigate cognitive biases toward either disputant. Experiments on VerdictBench show that CyberJurors outperforms state-of-the-art LLMs, MLLMs, and court simulators, while achieving stronger alignment with real-world jury voting patterns. Code and dataset are available at https://github.com/YanhuiS/CyberJurors and https://huggingface.co/datasets/piggi/VerdictBench.

Building on developments in machine learning and prior work in the science of judicial prediction, we construct a model designed to predict the behavior of the Supreme Court of the United States in a generalized, out-of-sample context. To do so, we develop a time evolving random forest classifier which leverages some unique feature engineering to predict more than 240,000 justice votes and 28,000 cases outcomes over nearly two centuries (1816-2015). Using only data available prior to decision, our model outperforms null (baseline) models at both the justice and case level under both parametric and non-parametric tests. Over nearly two centuries, we achieve 70.2% accuracy at the case outcome level and 71.9% at the justice vote level. More recently, over the past century, we outperform an in-sample optimized null model by nearly 5%. Our performance is consistent with, and improves on the general level of prediction demonstrated by prior work; however, our model is distinctive because it can be applied out-of-sample to the entire past and future of the Court, not a single term. Our results represent an important advance for the science of quantitative legal prediction and portend a range of other potential applications.

LLM-as-a-Judge (LLMaaJ) now underpins scalable evaluation, yet we lack a decisive test of a judge's qualification: can it recover a conversation's latent objective and know when that inference is trustworthy? LLMs degrade under irrelevant or long context; multi-turn jailbreaks further hide goals across turns. We introduce ObjexMT, a benchmark for objective extraction and metacognition. Given a multi-turn transcript, a model must return a one-sentence base objective and a self-reported confidence. Accuracy is computed via LLM-judge semantic similarity to gold objectives, converted to binary correctness by a single human-aligned threshold calibrated once on N = 100 items (tau^*=0.61). Metacognition is evaluated with ECE, Brier, Wrong-at-High-Conf, and risk-coverage. Across gpt-4.1, claude-sonnet-4, and Qwen3-235B-A22B-FP8 on SafeMTData_Attack600, SafeMTData_1K, MHJ, and CoSafe, claude-sonnet-4 attains the best objective-extraction accuracy (0.515) and calibration (ECE 0.296; Brier 0.324); gpt-4.1 and Qwen3-235B-A22B-FP8 tie at 0.441 but are overconfident (mean confidence approx0.88 vs. accuracy approx0.44; Wrong-at-0.90 approx48-52%). Performance varies by dataset (approx0.167-0.865). ObjexMT thus supplies an actionable test for LLM judges: when objectives are not explicit, judges often misinfer them with high confidence. We recommend exposing objectives when feasible and gating decisions by confidence otherwise. Code and data at https://github.com/hyunjun1121/ObjexMT_dataset.

Large language models increasingly justify legal decisions by naming the statute or precedent behind a verdict, treated as evidence that the decision follows from it. We test this directly: holding case facts fixed, we substitute the named legal authority for an unrelated one and decode a model's evolving verdict from its hidden states. Across seven open-weight models (8B-70B) and four benchmarks spanning judicial and contractual reasoning, when explicitly required to justify a verdict by naming the governing authority, models name the correct one in 66.7%-100% of generations, while the verdict changing when the authority changes is far less consistent: 0.0%-21.7% on CaseHOLD, 30.0%-76.7% on ECHR and SCOTUS, and 43.3%-50.0% on ContractNLI. Neither scale nor a purpose-built legal-reasoning model (a best-effort LoRA reproduction; Section 6) closes this gap. A red-teaming evaluation on five core models finds compliance with an adversarial instruction hidden in the case facts (73.3%-96.4%) exceeds verdict-swap sensitivity by a wide margin, holding without exception across model rankings. Naming a legal authority is thus a poor proxy for a verdict's dependence on it, while the same verdict remains separately vulnerable to adversarial manipulation. Both findings replicate across checks ruling out prompt-wording noise and confounded sampling, and bear directly on the use of generated legal explanations as compliance or audit artefacts.

Jev is a commercial System One model from TypeSafe AI that does not generate text: given a state and typed questions, it returns a choice from fixed options, a position on a rubric, or the probability that a statement is true, with probabilities the vendor describes as calibrated. Such models target small decisions in information access pipelines, such as routing queries, checking grounding, moderating content, or rating against a rubric. We evaluate Jev (jev-1.13.0) zero-shot on 37 datasets spanning classification, routing, natural language inference, reading comprehension, commonsense reasoning, moderation, legal clause analysis and rubric scoring, with one frozen template per dataset and full evaluation splits: 346,009 requests for under USD 10. For reference, we score Qwen3.8-27B and Gemma-4-E4B on identical requests via their exact next-token probabilities over the options. Jev reaches 95-99% accuracy on IMDB, SST-2, HellaSwag and ARC and 86.7% on Belebele across 122 languages. It beats Qwen on 27 of 37 datasets, with none of Qwen's nine leads outside the bootstrap intervals, and Gemma on all 37. All three models degrade on low-resource languages, fine-grained or noisy labels, and rubric-based quality judgments. Jev's choice probabilities are well calibrated and support selective prediction. Binary probabilities rank well but are poorly placed relative to a fixed 0.5 threshold; thresholds tuned on training data raise micro-F1 on UNFAIR-ToS from 0.50 to 0.75. Jev answers MMLU's calculation-heavy questions more accurately than other MMLU questions (94% vs. 91%), whereas both open models, and all three on C-Eval, find them harder. Rotating the options leaves Jev's accuracy unchanged and withholding the question drops it to near chance, ruling out shallow memorization but not memorized question-answer pairs. We release the code, harness and all raw responses.

Noise plagues many numerical datasets, where the recorded values in the data may fail to match the true underlying values due to reasons including: erroneous sensors, data entry/processing mistakes, or imperfect human estimates. We consider general regression settings with covariates and a potentially corrupted response whose observed values may contain errors. By accounting for various uncertainties, we introduced veracity scores that distinguish between genuine errors and natural data fluctuations, conditioned on the available covariate information in the dataset. We propose a simple yet efficient filtering procedure for eliminating potential errors, and establish theoretical guarantees for our method. We also contribute a new error detection benchmark involving 5 regression datasets with real-world numerical errors (for which the true values are also known). In this benchmark and additional simulation studies, our method identifies incorrect values with better precision/recall than other approaches.

Automated answer matching, which leverages LLMs to evaluate free-text responses by comparing them to a reference answer, shows substantial promise as a scalable and aligned alternative to human evaluation. However, its reliability requires robustness against strategic attacks such as guesswork or verbosity that may artificially inflate scores without improving actual correctness. In this work, we systematically investigate whether such tactics deceive answer matching models by prompting examinee models to: (1) generate verbose responses, (2) provide multiple answers when unconfident, and (3) embed conflicting answers with the correct answer near the start of their response. Our results show that these manipulations do not increase scores and often reduce them. Additionally, binary scoring (which requires a matcher to answer with a definitive "correct" or "incorrect") is more robust to attacks than continuous scoring (which requires a matcher to determine partial correctness). These findings show that answer matching is generally robust to inexpensive text manipulation and is a viable alternative to traditional LLM-as-a-judge or human evaluation when reference answers are available.

Large language model (LLM) judges are often used as rewards to train policies on objectives that deterministic verifiers cannot capture. However, these rewards are often collapsed to pass/fail ({0, 1}), which reports the verdict but not how well a response met each criterion. We model each pass/fail verdict as a score on an unreported scale, compared with one cutoff. A stretch of that scale moves every score proportionally toward or away from the cutoff, but never across it, so no verdict changes. A policy is therefore free to apply any stretch without changing anything the panel reports. Under a joint-Gaussian model, a third grade adds a second threshold and removes this affine stretch ambiguity. On MATH and SciBench outputs from one seven-criterion judge, all 14 constructed criterionwise stretches were invisible after binarization but visible with three grades. At n=1{,}024, a test given both population laws had at least 96.5% power at a 1.5times stress. Retaining grades closes one blind spot created by binarization, but verdicts alone remain insufficient as some changes are still indistinguishable from genuine improvement. These include arbitrary within-grade changes and fixed-covariance, loading-aligned mean shifts -- the signature of a sycophancy-shaped lift the panel reads as competence. The shared-factor reference approximation fit MATH and SciBench but not HealthBench, delineating its empirical scope. We recommend keeping at least three grades (for example, asking the judge whether each criterion is fully, partially, or not met and rewarding {0, 0.5, 1}), and externally validating gains along the remaining direction, which no finer scale removes.

AI chatbots are rapidly shaping how people encounter the news, yet no prior study has systematically measured how accurately these systems, with their proprietary search integrations and retrieval-synthesis pipelines, handle emerging facts across languages and regions. We present a 14-day (February 9-22, 2026) evaluation of six AI chatbots (Gemini 3 Flash and Pro, Grok 4, Claude 4.5 Sonnet, GPT-5 and GPT-4o mini) on 2,100 factual questions derived from same-day BBC News reporting across six regional services (US & Canada, Arabic, Afrique, Hindi, Russian, Turkish). The best systems achieve over 90% multiple-choice accuracy on questions about events reported hours earlier. The same systems, however, lose 11-13% under free-response evaluation, and 16-17% across the cohort. We further characterize three failure patterns. First, every model achieves its lowest accuracy on Hindi (79% vs. 89-91% elsewhere) and citations indicate an Anglophone retrieval bias (e.g., models answering Hindi queries cite English Wikipedia more than any Hindi outlet). Second, retrieval, not reasoning, failures drive over 70% of all errors. When models retrieve a correct source, they often extract the correct answer; the problem is to land on the right source in the first place. Third, models achieving 88-96% accuracy on well-formed questions drop to 19-70% when questions contain subtle false premises, with the most vulnerable model accepting fabricated facts 64% of the time. We also identify a detection-accuracy paradox: the best false-premise detector ranks second in adversarial accuracy (abstention rate), while a weaker detector ranks first, showing that premise detection and answer recovery are partially independent capabilities. Overall, these suggest that high accuracy can mask systematic regional inequity, near-total dependence on retrieval infrastructure, and vulnerability to imperfect queries real users pose.

Benchmarks for full-duplex spoken dialogue models score turn-taking with binary fixed-window rules that reward immediate response or silence by completeness of the prior turn. We argue that the appropriateness of a response offset, whether delayed silence or anticipatory overlap, is conditional on the speaker's latent intent, identifiable only from that speaker's behavior. We introduce TACT, a benchmark of 9,728 episodes and 73.2 hours from five dyadic corpora; each episode carries dialogue history, a per-speaker memory profile, and an annotator-derived posterior over six intent classes. Scoring replaces binary windows with a strictly proper threshold-weighted continuous ranked probability score whose weights are intent-conditioned timing kernels fitted to human floor-transfer-offset distributions, proving boundedness, consistency, and binary reduction. Across eleven systems the best model reaches 0.47 against a human topline of 0.86, is nearly invariant to speaker profiles, and TACT agrees with human judgments at Spearman 0.81 versus 0.46 for binary metrics.

While there are numerous benchmarks comparing the performance of modern language models (LMs), end-task evaluations often conflate notions of *factual accuracy* ("truth") and *reasoning ability* ("rationality", or "honesty" in the sense of correctly reporting implications of beliefs). Our goal is a dataset that clearly distinguishes these two notions. Our approach is to leverage and extend a collection of human-annotated *entailment trees*, engineered to express both good and bad chains of reasoning, and using a mixture of true and false facts, in particular including counterfactual examples, to avoid belief bias (also known as the "content effect"). The resulting dataset, called BaRDa, contains 3000 entailments (1787 valid, 1213 invalid), using 6681 true and 2319 false statements. Testing on four GPT-series models, GPT3(curie)/GPT3(davinici)/3.5/4, we find factual accuracy (truth) scores of 74.1/80.6/82.6/87.1 and reasoning accuracy scores of 63.1/78.0/71.8/79.2. This shows the clear progression of models towards improved factual accuracy and entailment reasoning, and the dataset provides a new benchmark that more cleanly separates and quantifies these two notions.

Why do language models sometimes prefer correct statements even when trained on mixed-quality data? We introduce the Compression--Consistency Principle: next-token prediction favors hypotheses that allow shorter and more internally consistent descriptions of the training data. Truth bias emerges only when false alternatives are structurally harder to compress. We test this using small GPT-2-style character-level transformers (3.5M--86M parameters) on synthetic math corpora with controlled mixtures of correct and incorrect rules. In the random-error setting, models strongly prefer correct completions in paired evaluation: 83.1% accuracy at balanced data and 67.0% even when correct rules appear in only 10% of the corpus. Replacing random errors with a coherent but mathematically incorrect rule system largely eliminates the preference (near-chance accuracy). In a more natural-language-like synthetic world, the effect is weaker but still present (57.7%). Additional experiments show that embedding verification steps can restore preference for correctness even at small scale, while increasing the number of consistent rules produces a graded improvement in accuracy. Our results suggest that what appears as a "truth bias" is largely a side effect of compression pressure and preference for internal consistency, rather than an intrinsic drive toward truth. Full code and data are available at https://github.com/Rai220/compression-drives-truth.

Large language model compliance systems are deployed on the assumption that a verdict depends on the regulatory rule it is given. We test this directly across five models and 20 regulatory and platform-policy domains: delete, swap, or negate the governing rule while holding the case fixed, and check whether the verdict changes (OCS) or the model's internal representation of compliance shifts at all (ICS-delta). Neither moves much: models' verdicts are often invariant to substantial perturbations of the supplied rule, and the guard model, evaluated here under a custom-rule adaptation of its native taxonomy, is the least rule-sensitive and least accurate of the five, barely above chance (51%, versus 90-92% for general-purpose models). This reflects easy cases more than blanket neglect: on cases where deleting the rule changes a previously correct model prediction, models do track it closely. Neither better prompting nor direct intervention on the model's internal representations closes this gap. Accuracy alone does not establish that a compliance verdict is grounded in the supplied rule.

Authorship verification (AV) is the task of determining whether two texts were written by the same author. In a forensic context, the strength of AV evidence can be quantified using likelihood ratios. Most AV methods are score-based and deriving well-calibrated likelihood ratios from these scores requires a separate calibration model. This, in turn, requires additional amounts of case-relevant data, which is often time-consuming to obtain and prepare. This study proposes two novel normalisation techniques, the Square Root Correction and the Hapax Correction, for deriving likelihood ratios from the AV method LambdaG without the need of a calibration model (Nini et al. 2026). These corrections are designed to mitigate the overestimation of evidential strength that may result from long or highly repetitive texts. Performance is evaluated against logistic regression calibration across fifteen corpora and a range of text lengths (100-9,500 tokens), using the log-likelihood ratio cost (Cllr). The proposed methods achieve performance comparable to logistic regression calibration, with the Hapax Correction outperforming it in approximately 45% of tests (weighted by corpora). Furthermore, performance was more frequently close (within 5%) when the Hapax Correction was outperformed by logistic regression calibration, compared with the reverse comparison. Eliminating the need to train a calibration model reduces data-requirements, time and complexity, thereby increasing the accessibility and transparency of forensic text comparison. This combination of empirical performance and practical advantages supports the adoption of the proposed methods in forensic settings.

Legal NLP benchmarks are overwhelmingly English-centric, leaving failure modes in morphologically rich, non-Latin-script languages undetected. We introduce UA-Legal-Bench, a five-task benchmark for evaluating large language models on Ukrainian legal reasoning, built from the Unified State Register of Court Decisions (EDRSR) -- one of the world's largest open judicial corpora (99.5 million decisions). The benchmark comprises: (1) case-type classification (4 classes, n=2,000), (2) judgment form classification (4 classes, n=2,000), (3) case-outcome prediction (6 classes, n=800), (4) legal norm extraction (n=1,794), and (5) cause category prediction (22 classes, n=1,871). We evaluate 11 LLMs (3B--675B) from five families under zero-shot and 3-shot prompting via AWS Bedrock with 158K API calls. Our results reveal sharply task-dependent few-shot effects: few-shot prompting improves judgment form classification by up to +38.6 pp but has mixed effects on outcome prediction. We show that accuracy is misleading on imbalanced legal tasks: the model with highest COP accuracy (62%) is a majority-class predictor (macro-F1: 23%), while the genuinely best model scores only 44% macro-F1. Within-family scaling analysis reveals that 8B models can match frontier performance on surface-level tasks but scaling thresholds vary dramatically across families. We release all data, prompts, and model predictions.

Accident, defect and outage investigations end with a decision that ordinary question answering never faces: whether the evidence gathered so far is enough to close the case. We study this decision for LLM investigators, which request evidence from a case file, revise their hypotheses, and either close the case with a conclusion grounded in what they read or leave it open and name what is missing. This judgment does not come with capability: an untrained 9B model overstates its evidence in 97% of its answers, and a frontier model that identifies the right cause in 84% of cases still overstates in 91% and closes 17 of the 41 cases whose official finding is "cause undetermined". Measuring it is also non-trivial: the source of a case largely predicts its label, and a rule that reads only the source reaches 83.0 balanced accuracy on our test cases. We therefore evaluate closure with three tests: closure accuracy, reported against this rule and within each source; evidence dependence, which removes the grounds of a conclusion and checks whether the model stops closing; and conclusion and gap quality, a judged checklist of what the model asserts and what it says is missing. We build Nautil, 731 audited cases from aviation, rail, maritime, chemical-safety and vehicle-defect reports and production server incidents, with teacher trajectories, an out-of-distribution test set and counterfactual evidence versions. Fine-tuning a 9B model on these trajectories makes its closures follow the evidence: removing the grounds lowers its closure rate by 26 points relative to a matched control, overstatement falls from 97% to 35%, and correct, non-overstated conclusions rise from 3% to 43%. Reinforcement learning that rewards only the closure decision then raises balanced accuracy from 69.2 to 83.3, on par with the teacher, and within-source accuracy from 60.4 to 74.1, at some cost in evidence dependence.

A recurring proposal in legal AI is to improve case-outcome prediction by fusing uncertainty tools (evidence graphs with belief propagation, sequential Bayesian odds updating, Dempster-Shafer combination, and conformal prediction) into one pipeline. We test this on 1,000 real European Court of Human Rights cases from LexGLUE and FairLex, predicting whether the Court found a Convention violation from the case's fact paragraphs. We compare three families across two frontier LLMs (Claude Opus 4.8 and GPT-5.5) as per-fact evidence estimators: (A) the raw LLM, (B) the LLM routed through the fusion pipeline, and (C) a term-frequency baseline through the same pipeline. Across roughly 4,750 tests we find: (1) on discrimination (AUROC around 0.83) the pipeline yields no improvement over either the raw LLM or the baseline; a frontier LLM used directly is the strongest single discriminator. (2) Naively composing an LLM with Bayesian-odds and Dempster-Shafer fusion more than doubles calibration error (ECE from about 0.16 to 0.46) via a prior-mismatch mechanism that replicates across both models. (3) Dempster-Shafer fusion is actively unsafe on long chains, committing confidently to wrong labels at below-chance accuracy; we recommend removing it. (4) The pipeline's genuine value is operational: routed through a conformal selective-prediction layer, the system decides which cases to automate and which to escalate. After removing Dempster-Shafer, recalibrating, and applying class-conditional risk control on the full 1,000-case set, the tuned engine auto-clears at 96.8 percent accuracy with 0.5 percent errors escaping and 96.3 percent caught for review, versus 85.9 / 3.8 / 72.1 for an untuned baseline. The contribution of such pipelines in law is calibrated trust, not sharper prediction.

Fine-tuning can improve legal question-answering accuracy without improving how models use law supplied in context. We study this distinction in bilingual Bangladeshi legal QA, where observed errors can arise from answer scoring, retrieval, or failure to use relevant law. We construct a hierarchy-preserving statutory corpus, 2,165 reviewed bilingual fine-tuning examples, and a 150-item supplied-law control. We evaluate six instruction-tuned models: Llama-3.2-1B, Llama-3.2-3B, Qwen3.5-0.8B, Qwen3.5-2B, Qwen3.5-4B, and Gemma-4-E2B, with three LoRA seeds per model. To separate effects, we combine constrained option-letter scoring, cyclic option rotation, and controlled removal of the governing provision. On 398 Bar Council outputs, an exact-line parser attributes an accuracy gain of 50.0\% to the Qwen3.5-2B seed-42 adapter, whereas option scoring yields only 3.0%. For Gemma-4-E2B, the two scoring methods favor different systems. When the governing provision is guaranteed to be present, five of six reference models improve by 14.7%-19.3% under the four-order criterion. Removing that provision reduces accuracy by 8.0%-15.3% for models and by 13.8%-14.9% points for their adapters. However, difference-in differences estimates show no increase in reliance on the governing provision after fine-tuning. Results show that legal adaptation claims require separating scorer, retriever, and model effects. Our Code and data are available at https://anonymous.4open.science/r/bangladesh-legal-qa-11E3

We investigate how looped transformers encode human preference, training lightweight evaluator heads on frozen Ouro-2.6B loop-iteration states on Anthropic HH-RLHF. v2: an erratum is prepended; the original manuscript is unchanged. A post-publication audit found the three headline results inflated by two independent evaluation errors. The 95.2% pairwise evaluator accuracy is a canonical-ordering artifact: the data were correctly split, but the evaluator learned to prefer the first-presented argument; its strict antisymmetrized accuracy on the full 8,552-pair test set is 63.9%. The 84.5% pairwise probe and the below-chance 21.75% pointwise probe were source-item leaks (orientation rows and pair partners crossing the train/test split); corrected pair-disjoint values are 56.5% and 54.2% -- above chance, so the "inverted polarity" finding is withdrawn. The central finding survives at much smaller magnitude: preference is decoded more accurately relationally than pointwise (paired +2.3 points, 95% CI [+1.3, +3.3]), and the antisymmetrized evaluator still beats the linear probe, but no corrected readout rivals end-to-end reward models. The methodological findings stand (constant-output degeneracy, flip test, swap-protocol metric deflation), with one correction: antisymmetrized accuracy, not antisymmetry correlation, certifies relational discrimination. The two errors are mutually invisible -- a split audit cannot see an ordering prior, antisymmetrization cannot see a leak -- so both checks are required. Full audit in the follow-up work (Kirin, 2026, in preparation).

Knowing domain rules does not guarantee applying them to a case. We study this distinction in traditional Chinese Bazi through 3,000 Chinese multiple-choice questions spanning 14 Theory and 11 Case categories. Six endpoint systems are evaluated, with primary results reported on a 2,492-item model-informed refinement. Theory accuracy exceeds Case accuracy for every system, and gaps of 16.60-29.56 percentage points remain when invalid responses are excluded. The contrast is more specific than a general case-reasoning deficit. Across six systems, Twelve Stages and Nayin reach mean accuracies of 89.10% and 88.62%, while Shensha Basics reaches 75.96%. Within Case, Luck Pillars averages 84.62%, but Career and Family Relations average only 36.98% and 38.19%. Overall rankings also conceal different category strengths. On the original 3,000 items, paired DeepSeek native/disabled comparisons associate native configurations with Theory gains of 6.53 and 12.20 points for Flash and Pro, respectively; Case changes are -3.67 and +1.27 points. These are provider-configuration associations, not isolated causal effects of reasoning. The results motivate task-specific evaluation of cultural-domain applications rather than reliance on aggregate knowledge scores. The benchmark measures agreement with a model-generated, model-verified answer key, not real-world predictive validity. Final-set results are post-selection descriptions, and incomplete provenance and expert validation constrain their interpretation.

This paper proposes a new metric to measure the calibration error of probabilistic binary classifiers, called test-based calibration error (TCE). TCE incorporates a novel loss function based on a statistical test to examine the extent to which model predictions differ from probabilities estimated from data. It offers (i) a clear interpretation, (ii) a consistent scale that is unaffected by class imbalance, and (iii) an enhanced visual representation with repect to the standard reliability diagram. In addition, we introduce an optimality criterion for the binning procedure of calibration error metrics based on a minimal estimation error of the empirical probabilities. We provide a novel computational algorithm for optimal bins under bin-size constraints. We demonstrate properties of TCE through a range of experiments, including multiple real-world imbalanced datasets and ImageNet 1000.

This research introduces the Judge's Verdict Benchmark, a novel two-step methodology to evaluate Large Language Models (LLMs) as judges for response accuracy evaluation tasks. We assess how well 54 LLMs can replicate human judgment when scoring responses from RAG (Retrieval-Augmented Generation) or Agentic pipelines against ground truth answers. Our methodology progresses from traditional correlation analysis to comprehensive Cohen's Kappa analysis that measures actual agreement patterns. The two-step approach includes: (1) a correlation test that filters judges with strong alignment, followed by (2) a human-likeness test using z-scores to identify two distinct judgment patterns: human-like judgment (|z| < 1) that mimics natural human variation, and super-consistent judgment (z > 1) that exceeds typical human-to-human agreement levels. This methodology reveals that 27 out of 54 tested LLMs achieve Tier 1 performance: 23 models exhibit human-like patterns that preserve the nuances of human judgment, while 4 models demonstrate super-consistent behavior, a pattern that could indicate either enhanced reliability or oversimplification of complex judgments. Testing 43 open-source models (1B-405B parameters) and 11 closed models (GPT, Gemini, Claude variants), we demonstrate that judge excellence is not solely dependent on model size but on specific training strategies. Our key contributions include: (1) establishing that correlation alone is insufficient for judge evaluation, (2) introducing a "Turing Test for judges" based on agreement patterns, and (3) providing a standardized benchmark for classifying LLM judges into distinct performance tiers for different evaluation needs.

Almost every paper on LLM jailbreaks and prompt injection reports an attack-success rate (ASR), and that number is assigned not by people but by an automated judge: either a safety classifier trained for the task, or a general chat model prompted to grade. The judge is rarely checked. We check it. Using 596 human-labeled completions from the HarmBench classifier validation set, we compare the two judge families against human majority votes and then attack them. The two families fail in opposite ways. The dedicated classifier over-flags (precision 0.835, recall 0.974); three different LLM-as-judges keep high precision (0.81 to 0.94) but show erratic recall (0.06 to 0.65), so the same responses produce very different ASR depending on which judge scores them. The two families also differ sharply in robustness. Wrappers that leave the harmful text untouched and only add benign framing flip every LLM-judge between 57% and 100% of the time, and a single prepended refusal sentence accounts for much of this (39% to 88%). The dedicated classifier resists these surface attacks (at most 6.7%), but a white-box GCG attack on its open weights flips 70% of confident true positives (21 of 30; 95% CI 54 to 86%) even at a small optimization budget. A two-annotator audit confirms the attacks leave the harm intact: every one of 80 sampled flips still contained the harmful content. Because a large and growing share of reported ASR comes from LLM-judges, many such numbers are unreliable both on average and under deliberate pressure. We recommend that papers report judge precision and recall on a human-labeled slice, report ASR corrected for judge precision, and include an adversarial check of the judge. Our code is released.

Decision models support routing, guardrails, and output verification in LLM systems. However, item accuracy alone cannot establish whether models make correct decisions across controlled variations or assign reliable confidence to their predictions. We introduce DecisionPivot, a diagnostic benchmark comprising 48 tasks and 40,033 items across seven decision roles. Its core track contains 7,800 items from 13 generated task families, organized into contrast groups with computed answers verified by independently implemented solvers. The complementary reference track contains 32,233 items from 35 public test sets, preserving their original evaluation metrics. We evaluate 40 decision models and 14 general models using documented, model-specific protocols, assessing item and contrast-group accuracy, probability ordering, calibration, and empirical selective coverage. Our results reveal substantial differences obscured by aggregate scores: two 27B models separated by only 2.6 points on the reference track achieve contrast-group accuracies of 70.1% and 44.2%. Across 2,400 binary contrast pairs, Perplexity Decider correctly ranks the positive member above the negative member in 92.3% of pairs but answers both members correctly in only 74.1%, exposing a gap between probability ordering and decision correctness. Models with similar item accuracy also differ in the reliability of their high-confidence predictions. On a separate 1,296-item subset, GLM-5.3 achieves 93.5\% contrast-group accuracy at a higher reasoning setting, compared with 81.5% at its lowest effort. By linking errors to pivotal details and difficulty levels, DecisionPivot provides fine-grained diagnostics of decision failures that aggregate evaluation alone cannot reveal.

Robustness evaluation must examine diverse visual perturbations, while benchmarks cover only some real-world conditions and physical testing is costly. Paired evaluations link clean and perturbed predictions for the same image, capturing changes in correctness, confidence, and acceptance beyond aggregate accuracy. We investigate how this image correspondence supports two needs in robustness evaluation: interpreting paired evaluation results and prioritizing samples for physical testing. To interpret paired evaluation results, we fix both sets of prediction records and vary their correspondence within each class. We prove that classwise correct-correct counts give the same sharp bounds on lost acceptance and mean true-class probability decrease among retained-correct inputs as any feasible five-state refinement. Distinguishing persistent from changed wrong answers can further constrain accepted-error transitions, while shared correspondence can establish policy orderings left unresolved by separate cost intervals. To prioritize samples for physical testing, we retain each image's synthetic responses and rank clean-correct images by their mean true-class probability under corruption. Across 44 classifiers, testing the highest-risk 20% finds 67% and 45% of failures under mild screen and print recaptures, versus 58% and 36% for clean confidence and 60% and 37% for an equal-size natural-transformation average. With both probability averaging and an A3Rank scoring adaptation, the tested corruption set yields higher mean failure recall than the natural-transform set; differences between scores depend on the source and budget. Together, these findings show that the value of correspondence depends on the evaluation objective: classwise counts suffice for specified reliability bounds, while image-specific synthetic responses improve the allocation of physical tests within the evaluated pool.

Benchmark contamination is diagnosed with n-gram overlap, likelihood-based membership inference, or canary strings, and each needs something usually unavailable: the training corpus, a well-chosen test statistic, or foresight at release. A recent alternative reads it off a linear probe on internal activations. We show the natural way to do this does not work, specify one that survives measurement, then find that the correction making it work carries more variance than the null it is tested against. The protocol reports a zero-sum contrast on the depth profile of probe accuracy, recentred on a level-matched placebo baseline, tested against a label-permutation null, with the reference set twice the size of the suspect set. Each choice replaces a simpler alternative we rejected on measurement. Reporting the level of excess separability rather than its shape makes the false positive rate track the size of the analyst's own control set, 0.03 to 0.99 under a true null. Contrasting against a flat depth profile rejects a true null 0.72 of the time when surface decodability rises with depth, and loses all power when it falls. On real transformers the protocol fails a test the simulations did not pose. The recentring subtracts an estimate, and the permutation null holds it fixed. Re-estimated across split seeds on four audits of contaminated checkpoints, its standard deviation is 1.30 to 1.56 times the null's own in every arm: what is subtracted to remove a bias is more variable than what it corrects. The one nominally significant result, p = 0.0075, becomes 0.0745 once that variance is propagated, and no verdict is issued. The simulations missed this because their surface key is the covariate driving item variation; on real text it is a proxy, and degrading key quality in simulation reproduces it. We add a companion measurement and a widened null. No arm shows contamination.

Jev has attracted considerable attention for its rapid, generalizable decision-making, yet its medical reliability remains underexplored. To address this gap, our study compares various types of system-one decision models across 15 medical datasets comprising 8,742 instances under a unified protocol. Beyond accuracy, we assess decision stability and the ability to recognize unreliable decisions. Our results show that Jev rivals leading models on primarily text-driven tasks but is less effective on numerically driven tasks, revealing a distinct capability boundary. Under question-format variations, Jev maintains strong decision consistency and small accuracy fluctuations. StartLux-27B exhibits comparable consistency, while D3-27B achieves higher overall accuracy and a lower mean decision reversal rate. But these strengths do not extend to reliable abstention awareness: most evaluated models show limitations in both recognizing missing correct answers and using optional abstention. Moreover, we find that Jev's probability-based answer selection can be improved by changing how decisions are scored: normalizing option-wise binary scores yields higher retained accuracy than choice scoring. Taken together, our findings provide early guidance for improving and applying decision models in medicine.

Large Language Models (LLMs) and other automated techniques have been increasingly used to support software developers by generating software artifacts such as code snippets, patches, and comments. However, accurately assessing the correctness of these generated artifacts remains a significant challenge. On one hand, human evaluation provides high accuracy but is labor-intensive and lacks scalability. On the other hand, many automatic evaluation metrics are scalable and require minimal human effort, but they often fail to accurately reflect the actual correctness of generated software artifacts. In this paper, we present SE-Jury, the first evaluation metric for LLM-as-Ensemble-Judge specifically designed to accurately assess the correctness of generated software artifacts. SE-Jury first defines five distinct evaluation strategies, each implemented by an independent judge. A dynamic team selection mechanism then identifies the most appropriate subset of judges as a team to produce a final correctness score through ensembling. We evaluate SE-Jury across a diverse set of software engineering (SE) benchmarks that span three popular SE tasks: code generation, automated program repair, and code summarization. Results demonstrate that SE-Jury consistently achieves a higher correlation with human judgments, with improvements ranging from 29.6% to 140.8% over existing automatic metrics. SE-Jury reaches agreement levels with human annotators that are close to inter-annotator agreement in code generation and program repair. These findings underscore SE-Jury's potential as a scalable and reliable alternative to human evaluation in these SE tasks.

Legal judgment prediction is the task of automatically predicting the outcome of a court case, given a text describing the case's facts. Previous work on using neural models for this task has focused on Chinese; only feature-based models (e.g., using bags of words and topics) have been considered in English. We release a new English legal judgment prediction dataset, containing cases from the European Court of Human Rights. We evaluate a broad variety of neural models on the new dataset, establishing strong baselines that surpass previous feature-based models in three tasks: (1) binary violation classification; (2) multi-label classification; (3) case importance prediction. We also explore if models are biased towards demographic information via data anonymization. As a side-product, we propose a hierarchical version of BERT, which bypasses BERT's length limitation.

Large language models (LLMs) have achieved expert-level performance on standardized examinations, yet multiple-choice accuracy poorly reflects real-world clinical utility and safety. As patients and clinicians increasingly use LLMs for guidance on complex conditions such as pancreatic cancer, evaluation must extend beyond general medical knowledge. Existing frameworks, such as HealthBench, rely on simulated queries and lack disease-specific depth. Moreover, high rubric-based scores do not ensure factual correctness, underscoring the need to assess hallucinations. We developed a human-in-the-loop pipeline to create expert rubrics for de-identified patient questions from the Pancreatic Cancer Action Network (PanCAN). The resulting benchmark, PanCanBench, includes 3,130 question-specific criteria across 282 authentic patient questions. We evaluated 22 proprietary and open-source LLMs using an LLM-as-a-judge framework, measuring clinical completeness, factual accuracy, and web-search integration. Models showed substantial variation in rubric-based completeness, with scores ranging from 46.5% to 82.3%. Factual errors were common, with hallucination rates (the percentages of responses containing at least one factual error) ranging from 6.0% for Gemini-2.5 Pro and GPT-4o to 53.8% for Llama-3.1-8B. Importantly, newer reasoning-optimized models did not consistently improve factuality: although o3 achieved the highest rubric score, it produced inaccuracies more frequently than other GPT-family models. Web-search integration did not inherently guarantee better responses. The average score changed from 66.8% to 63.9% for Gemini-2.5 Pro and from 73.8% to 72.8% for GPT-5 when web search was enabled. Synthetic AI-generated rubrics inflated absolute scores by 17.9 points on average while generally maintaining similar relative ranking.

The increasing reliance on AI-driven solutions, particularly Large Language Models (LLMs) like the GPT series, for information retrieval highlights the critical need for their factuality and fairness, especially amidst the rampant spread of misinformation and disinformation online. Our study evaluates the factual accuracy, stability, and biases in widely adopted GPT models, including GPT-3.5 and GPT-4, contributing to reliability and integrity of AI-mediated information dissemination. We introduce 'Global-Liar,' a dataset uniquely balanced in terms of geographic and temporal representation, facilitating a more nuanced evaluation of LLM biases. Our analysis reveals that newer iterations of GPT models do not always equate to improved performance. Notably, the GPT-4 version from March demonstrates higher factual accuracy than its subsequent June release. Furthermore, a concerning bias is observed, privileging statements from the Global North over the Global South, thus potentially exacerbating existing informational inequities. Regions such as Africa and the Middle East are at a disadvantage, with much lower factual accuracy. The performance fluctuations over time suggest that model updates may not consistently benefit all regions equally. Our study also offers insights into the impact of various LLM configuration settings, such as binary decision forcing, model re-runs and temperature, on model's factuality. Models constrained to binary (true/false) choices exhibit reduced factuality compared to those allowing an 'unclear' option. Single inference at a low temperature setting matches the reliability of majority voting across various configurations. The insights gained highlight the need for culturally diverse and geographically inclusive model training and evaluation. This approach is key to achieving global equity in technology, distributing AI benefits fairly worldwide.

Language models often receive a question together with a claim about what another source answered. We audit whether such claims destabilize answers in multiple-choice question answering. For each item, we hold one wrong option fixed across misleading conditions and vary the cue template attached to it. We introduce neutral-conditioned misleading cue adoption rate (NC-MCAR), which measures switches to that option only on valid cued trials where the same model first selected the gold answer under a neutral prompt. This is a measure of answer instability, not proof that the model knew the answer or that all deference is irrational. We evaluate four instruction-following models on MMLU-Pro and IndicMMLU-Pro in English, Hindi, Bengali, Tamil, and Telugu. Across 220{,}000 outputs, the expert template yields 41.1\% aggregate NC-MCAR, compared with 12.5\% for the majority template. These two conditions use the same wrong option and final instruction. Filler accuracy remains well above expert-wrong accuracy, while correct-cue prompts have high valid-response accuracy. The audit documents answer instability relevant to grounding under the tested forced-choice prompts: a bare, unverified source claim can outweigh an answer that was previously consistent with the task evidence.

Diagnosing 802.11 packet captures requires expert protocol knowledge, is slow, inconsistent across engineers, and unscalable. LLM-based approaches sound plausible but fabricate protocol events absent from captures (especially truncated traces), produce uncalibrated confidence scores, and suffer evaluation bias when golden references are co-produced by the model under test. We introduce PROBE (Protocol Reasoning Over evidence-Based Ensembles), a multi-stage pipeline addressing all three failures. It integrates (i) deterministic PCAP-to-text normalization with frame-level verifiability, (ii) multi-run, multi-candidate ensembles with optional cross-model second opinion and progressive obfuscation, (iii) a verdict-aware evidence framework treating absence of failure evidence as contributing evidence, and (iv) a fully deterministic composite reliability score from evidence validity, run-to-run stability, and cross-model agreement without LLM self-assessment. On 87 enterprise Wi-Fi captures (104 capture-reviewer pairs), single-pass LLM analysis raises weighted evidence F1 from 0.871 (expert baseline) to 0.912 but misses critical frames in 35% of cases. Naive ensemble voting drops below baseline (0.842) as majority voting amplifies conservative verdicts: 50% of confirmed failures are misclassified as 'no issue' or 'insufficient evidence.' Adding evidence-grounded reconciliation achieves 0.957 F1, a 96% auto-accept rate, and a worst-case floor above 0.70. LLM self-reported confidence clusters at 0.95 regardless of difficulty (71% report exactly 0.95), confirming it is uninformative. We also introduce a model-agnostic evaluation framework using per-field assertion matching, eliminating circular bias from model-co-produced golden references.

In 2023, a New York judge sanctioned two attorneys in Mata v. Avianca for filing a brief with hallucinated citations generated by ChatGPT. Such failures are largely caught by database lookups; the harder problem is detecting citations that point to real cases but do not support the propositions for which they are offered -- a failure mode that existing evaluations of LLMs for legal use cases largely overlook. In this paper, we study proposition-level citation support verification through controlled perturbations of real legal citations obtained from two legal corpora, either replacing the cited case or changing only the pinpoint page within the same case. We evaluate fourteen model configurations on the resulting examples. Models catch 93-100% of wrong-case corruptions. They catch only 37-61% of wrong-pinpoint corruptions on court opinions and 52-83% on legal briefs. When models fail to catch wrong-pinpoint corruptions, they accept the citation based on topical overlap rather than page-level support. Scale and extended reasoning narrow the gap but do not close it: GPT-5.4 with high reasoning effort still misses 40% of pinpoint mismatches on court opinions and 18% on briefs. Prompting the model to verify support at the cited page improves recall, but it also raises the false positive rate. Recognizing the right legal topic and verifying support for the cited proposition are distinct capabilities, and current models conflate them.

Large language models can arrive at the same answer through reasoning paths that are unstable, contradictory, or difficult to rank consistently -- a failure mode especially prevalent in multi-step deductive reasoning. Existing methods assess reliability primarily through output dispersion -- measuring how much sampled answers differ -- but this discards a complementary signal: whether the model can consistently rank competing reasoning candidates. We propose structural uncertainty, a consistency-aware framework derived from the stability of self-preference-induced rankings over sampled reasoning solutions. Given a query, we generate multiple candidate solutions and ask the model to judge pairwise preferences among its own outputs. We aggregate self-preferences into ranking distributions via Bradley-Terry modeling with PageRank, and decompose the signal into two entropy-based components: across-trial ranking instability and within-trial candidate ambiguity. Across five LLMs and eight benchmarks, structural signals provide information complementary to answer dispersion: on logical and mathematical reasoning tasks, the combination improves identification of unreliable instances, while on factual retrieval the structural signal collapses toward uniformity, diagnosing a regime boundary where reasoning-level consistency evaluation is uninformative. The two components relate differently to accuracy: within-trial ambiguity correlates positively with correctness -- consistent with settings where multiple plausible solution paths remain competitive -- while across-trial instability correlates negatively, signaling unreliable reasoning. Structural uncertainty is best understood not as a universal confidence estimator, but as a regime-sensitive evaluator of logical reasoning consistency.

Single-token typed-decision models answer a schema question by reading the logits of a few one-letter answer codes at a single position: they are fast and return a probability for every allowed answer, but they are trained with plain cross-entropy that ignores most of the structure in their training data. We study such a model whose data is curated as contrastive pairs---two contexts that differ in one edited fact that flips the answer---each carrying a machine-checked certificate that deleting the decisive sentence makes the fact unknown. We propose PACT, which turns this structure into four training terms that need no new annotation: a difference-in-differences margin over each pair that is invariant to any shared logit offset, a permutation-consistency term against answer-code position bias, an evidence-necessity term on certificate-verified ablated contexts, and an ordinal transport cost for rubric fields, plus a three-parameter contextual temperature. On a frozen 324-item holdout with three seeds, PACT matches the published recipe in accuracy (84.6% vs. 85.2%; McNemar p ge 0.50 at every seed) while giving the lowest position bias of all runs (answer flips under relabelling 9.8% vs. 13.8%) and the lowest ordinal error on rubric fields (MAE 0.232 vs. 0.311). Against a control with the same optimiser and schedule but cross-entropy only, PACT is significantly more accurate at two of three seeds, halves the seed-to-seed spread and lowers NLL by 26%. Seed-matched ablations and pre-specified falsification tests locate these gains precisely: no single term raises raw accuracy, and the method's value lies in robustness and stability rather than headline accuracy. Code, data splits, trained adapters, and all run records are available at https://github.com/BennyLinntu/PACT-Pairwise-Anchored-Calibrated-Tuning-for-Single-Token-Typed-Decisions.

Recent advances in LegalAI have primarily focused on individual case judgment analysis, often overlooking the critical appellate process within the judicial system. Appeals serve as a core mechanism for error correction and ensuring fair trials, making them highly significant both in practice and in research. To address this gap, we present the AppealCase dataset, consisting of 10,000 pairs of real-world, matched first-instance and second-instance documents across 91 categories of civil cases. The dataset also includes detailed annotations along five dimensions central to appellate review: judgment reversals, reversal reasons, cited legal provisions, claim-level decisions, and whether there is new information in the second instance. Based on these annotations, we propose five novel LegalAI tasks and conduct a comprehensive evaluation across 20 mainstream models. Experimental results reveal that all current models achieve less than 50% F1 scores on the judgment reversal prediction task, highlighting the complexity and challenge of the appeal scenario. We hope that the AppealCase dataset will spur further research in LegalAI for appellate case analysis and contribute to improving consistency in judicial decision-making.

Text-output scores alone do not show whether quantization preserves performance on speech tasks whose target labels cannot be recovered from the transcript. We evaluate fixed mixed 4/8-bit Qwen2-Audio-7B-Instruct allocations averaging 6 and 7 bits per parameter on 508 English-to-German FLEURS utterances and on 512 RAVDESS emotion clips from 16 speakers. The BLEU and chrF differences from half precision (FP16) have intervals that include zero for both allocations. On RAVDESS, the same two sentences occur equally often with every emotion label. The absolute accuracy differences from FP16 are -3.71% for 6 bit and -1.17% for 7 bit. The 6-bit speaker interval excludes zero and an exact two-sided sign-flip test gives p=0.0148; the 7-bit interval includes zero. Same-budget controls do not identify either selected allocation as best. This case study shows why translation scores and performance on tasks beyond the transcript need separate evaluation.

Many language-based applications need a probability distribution over a small set of decisions rather than an open-ended response. We present Chinese Decision, a family of Chinese-language decision models that adapts pretrained causal language models to this interface. Each question is compiled into a shared instruction-and-candidate prompt; a single forward pass reads the final-position logits of the candidate letters and normalizes them over the valid options, without autoregressive answer generation. The interface covers Boolean judgments, categorical choices, and ordinal scores. We report three completed members built on Qwen3.5 0.8B, 2B, and 4B backbones, each trained for one epoch on the same 13.048 million decisions and released with a validation-fitted temperature and a Q8_0 quantization. On the full 307,900-decision CJ-Bench, the 4B model reaches 85.97% overall accuracy, 75.69% general-domain accuracy, and 84.00% average accuracy across medicine, law, and finance with a single checkpoint, above every reported baseline in each domain, at 1.00% expected calibration error. Between the 2B and 4B members, which share data, objective, and minimum batch, parent-clustered paired bootstrap intervals show gains in all four domains, largest in the two low-resource domains (+8.5 and +7.1 points), whereas the 2B gain over 0.8B in law is not statistically resolved. Analyses of the stored predictions further show that a single global temperature lowers pooled calibration error while worsening some domains, that larger members rank their own errors better for selective prediction, and that merging and quantization each change 0.4-1.1% of top-1 predictions while leaving aggregate metrics nearly unchanged. All comparisons rest on single training runs and imported baselines.

Pass@k measures whether a model reaches a correct answer under repeated sampling, but never how: a lucky guess counts the same as sound reasoning. CoT-Pass@k was proposed to close that gap, adding an LLM-as-judge that must assess a solution's reasoning chain before it counts. Its value rests entirely on one assumption: that the judge catches flawed reasoning. That assumption has never been tested inside the metric that depends on it, and never outside English, though the metric's claims concern models used in many languages. We report the first audit of that verification step, run under the metric's own protocol on a multilingual suite of five mathematical benchmarks in English, Turkish and Portuguese, two of them natively written. We corrupt correct solutions with deterministic edits that damage the chain and the final answer separately. We observe that all three judges accept corrupted chains almost as often as clean ones. V4-Flash and Qwen3.6 reject a solution sharply only when its final answer is wrong and accept a wrong answer more readily when the chain agrees with it; the metric's own judge accepts most wrong answers as well. Our study shows that chain-answer agreement dominates the two larger judges' verdicts and that all three fail to reliably detect the tested reasoning errors. Consequently the difference Pass@k - CoT-Pass@k averages 19.7 points on an earlier solver generation but only 4.1 on the current one. What little remains depends on the token budgets on both sides and on the generation mode; raising the generation budget moves Pass@64 by more than fifty points while the difference stays at zero. We close with two checks any judged reasoning metric should pass before its numbers are read as evidence about reasoning.

Aggregate accuracy summarizes how often a model is correct, but not which judgments remain correct when requests change. We evaluate Jev and nine language models on ContractNLI, with repeated requests that preserve the contract and target while varying visible hypotheses, requested answers, and output order. A four-model follow-up adds an equal-call repetition control and coverage of the remaining test contracts. Corrections and regressions can cancel, leaving unchanged accuracy despite changed decisions; consistent answers can also preserve errors. Majority voting over recorded responses yields small, uncertain gains, with repeated wrong answers accounting for much of the observed error. Gold-class diagnostics further reveal different error profiles behind aggregate model rankings. Resource comparisons add distinct trade-offs: Jev is cheapest and fastest for the joint baseline, while hosted language models achieve higher accuracy. Together, these findings connect decision-level evaluation to whether additional calls improve correctness and what the resulting decisions cost.

Large language models are increasingly deployed as automated judges for evaluating other models, yet the stability of their verdicts under semantically equivalent prompt paraphrases remains unmeasured. We introduce JudgeSense, a framework and benchmark for quantifying this property via the Judge Sensitivity Score (JSS), defined as the fraction of paraphrase pairs on which a judge returns an identical decision. Evaluating nine judge models on 494 validated paraphrase pairs, we find that coherence is the only task where judges meaningfully differ, with JSS ranging from 0.389 to 0.992. On factuality, all judges cluster near JSS about 0.63, driven by a polarity-inverted prompt artifact; after correction, factuality JSS rises to about 0.9. Pairwise tasks (preference and relevance) exhibit degenerate always-A behavior in 8 of 9 judges, indicating strong position bias. Model scale does not predict consistency. We release code, decision logs, and a validated paraphrase dataset to support standardized JSS reporting.

Principle-based regulation, with evaluative standards such as "fair, clear, and not misleading" or "deliver good outcomes", cannot be reduced to binary predicates, and LLM-as-judge is increasingly used as the substitute. Our position is that any such judge must be evaluated on four axes: accuracy, paraphrase robustness, adversarial robustness, and calibration. We release Principle-Bench, 168 cryptoasset financial-promotion scenarios mapped to two UK FCA principles, with paraphrase, adversarial keyword-stuffing, and boundary perturbations authored under a pre-registered rubric; the first benchmark covering all four axes for principle-based regulation. We also introduce Ceca (Calibrated Exemplar-Cluster Assessment): a calibrated, auditable assessor that emits exact per-exemplar counterfactual attributions. Across keyword counting, three sentence-transformer embedders, an open-weight LLM-judge, and a calibrated cascade, no method dominates all four axes. A 120B LLM-judge, strongest on benign inputs, loses 47 accuracy points (0.74 to 0.27) on keyword-stuffed Consumer Duty inputs: "compliance theatre." A second judge from a different model family agrees only at Cohen's kappa = 0.16 on that split, localising the failure to the model rather than the corpus. Any deployment-grade LLM-judge for principle-based regulation must report per-principle adversarial deception and post-hoc calibration alongside aggregate accuracy.

If machine learning models were to achieve superhuman abilities at various reasoning or decision-making tasks, how would we go about evaluating such models, given that humans would necessarily be poor proxies for ground truth? In this paper, we propose a framework for evaluating superhuman models via consistency checks. Our premise is that while the correctness of superhuman decisions may be impossible to evaluate, we can still surface mistakes if the model's decisions fail to satisfy certain logical, human-interpretable rules. We instantiate our framework on three tasks where correctness of decisions is hard to evaluate due to either superhuman model abilities, or to otherwise missing ground truth: evaluating chess positions, forecasting future events, and making legal judgments. We show that regardless of a model's (possibly superhuman) performance on these tasks, we can discover logical inconsistencies in decision making. For example: a chess engine assigning opposing valuations to semantically identical boards; GPT-4 forecasting that sports records will evolve non-monotonically over time; or an AI judge assigning bail to a defendant only after we add a felony to their criminal record.

The appearance of Jev marked the era of System One Models, foundation models that return structured decisions with probability distributions rather than text. Aside from low cost and great speed, Jev's central promise is that these probabilities are calibrated: such claim is not backed by any public test and available external benchmarks evaluate confidence calibration, not whether every returned option probability has the right numerical meaning. To tackle this issue, we introduce Sys1Cal-v1, a dataset of True/False questions about a proposition A for which the exact probability P(A) is known by construction. Each item is queried through the three Jev primitives - Noul, Choice and Score - and evaluated by total variation distance from the ground-truth distribution, which can be used to estimate a soft accuracy of System One Models. We showcase the utility of Sys1Cal-v1 as a benchmark dataset by evaluating Jev and SemIf, an open-source Choice-style baseline. In this work, however, we focus even more deeply on Jev, by studying the calibration of its Score and Choice answers. In particular, we discover a peculiar behaviour that can be explained by assuming that Jev suppresses a third truth value, going beyond True and False. In other words, in Choice answers, P(A) and P(neg A) are presented as if P(A)+P(neg A)=1, while a term P(U)neq0 is missing in the sum. Recovering P(U) leads to an improvement of median soft accuracy in Choice answers from 0.771 to 0.978, suggesting that, even in binary decisions, Jev wants to answer with a third option:``I don't know''.

Large language models (LLMs) have shown impressive capabilities across diverse tasks, yet their performance on jurisdiction-specific legal reasoning remains underexplored. We present TW-LegalBench that utilizes Taiwanese legal system's rich official corpus open to the public to fill the gap in evaluating LLMs on Taiwanese law, among common-law benchmarks that focus on English sources and civil-law benchmarks focusing on sources of Simplified Chinese. TW-LegalBench comprises three task types: (1) over 16,000 multiple-choice questions (MCQs) across five years of official examinations in 18 professional domains; (2) 117 open-ended essay questions (OEQs) from examinations for legal professionals with official scoring rubrics; and (3) more than 14,000 legal judgment prediction (LJP) instances covering hundreds of crime categories. We evaluate 13 LLMs using accuracy for MCQs, a decomposed LLM-as-Judge framework based on the scoring rubric points for OEQs, and metrics for sentencing accuracy and statute citation for LJP. Our results reveal that top-performing models exceed the passing threshold for qualified lawyers (passing rate: 11%) but fall short of that for judges and prosecutors (passing rate: 1~2%). For LJP, while models demonstrate reasonable verdict type accuracy and sentence prediction capability, they struggle to cite exact legal articles. These findings highlight that reliable legal text generation remains challenging for LLMs, even though their performance on qualification examinations approaches human level.

Verifying the final answer of a long reasoning trace may show that the trace is wrong but it does not distinguish three cases. The problem may lie beyond the model's capability, another attempt would succeed, or one step in an otherwise recoverable trace made the trace fail. Standard hidden-state probes are trained on final-answer correctness, a label that conflates these cases. Monte Carlo rollouts distinguish the cases and locate the failing step at additional inference cost. We test the hidden states of 4B and 8B reasoning models for the failure type and the failing step and compare each probe with the strongest baseline that uses no hidden states. On incorrect 8B traces, the confidence probe, a calibrated correctness probe at a midpoint cutoff, misses 81% of cases in which a single step makes the trace unrecoverable and 47% of cases in which another attempt would succeed. A probe with a different training design over the same states reverses the ordering of these two kinds of failure, so either ordering can be read from those states. At both scales, no single tested probe locates the failing step more accurately than a rule based only on trace length, and at 4B a probe trained to predict that step fails to outperform this rule in any of 10 runs on identical traces. The confidence probe therefore indicates that an answer is wrong, but its failure-type ordering depends on its training design.

Reliable probability estimation is of crucial importance in many real-world applications where there is inherent (aleatoric) uncertainty. Probability-estimation models are trained on observed outcomes (e.g. whether it has rained or not, or whether a patient has died or not), because the ground-truth probabilities of the events of interest are typically unknown. The problem is therefore analogous to binary classification, with the difference that the objective is to estimate probabilities rather than predicting the specific outcome. This work investigates probability estimation from high-dimensional data using deep neural networks. There exist several methods to improve the probabilities generated by these models but they mostly focus on model (epistemic) uncertainty. For problems with inherent uncertainty, it is challenging to evaluate performance without access to ground-truth probabilities. To address this, we build a synthetic dataset to study and compare different computable metrics. We evaluate existing methods on the synthetic data as well as on three real-world probability estimation tasks, all of which involve inherent uncertainty: precipitation forecasting from radar images, predicting cancer patient survival from histopathology images, and predicting car crashes from dashcam videos. We also give a theoretical analysis of a model for high-dimensional probability estimation which reproduces several of the phenomena evinced in our experiments. Finally, we propose a new method for probability estimation using neural networks, which modifies the training process to promote output probabilities that are consistent with empirical probabilities computed from the data. The method outperforms existing approaches on most metrics on the simulated as well as real-world data.

The goal of two-sample tests is to assess whether two samples, S_P sim P^n and S_Q sim Q^m, are drawn from the same distribution. Perhaps intriguingly, one relatively unexplored method to build two-sample tests is the use of binary classifiers. In particular, construct a dataset by pairing the n examples in S_P with a positive label, and by pairing the m examples in S_Q with a negative label. If the null hypothesis "P = Q" is true, then the classification accuracy of a binary classifier on a held-out subset of this dataset should remain near chance-level. As we will show, such Classifier Two-Sample Tests (C2ST) learn a suitable representation of the data on the fly, return test statistics in interpretable units, have a simple null distribution, and their predictive uncertainty allow to interpret where P and Q differ. The goal of this paper is to establish the properties, performance, and uses of C2ST. First, we analyze their main theoretical properties. Second, we compare their performance against a variety of state-of-the-art alternatives. Third, we propose their use to evaluate the sample quality of generative models with intractable likelihoods, such as Generative Adversarial Networks (GANs). Fourth, we showcase the novel application of GANs together with C2ST for causal discovery.

Bail decisions are among the most frequently adjudicated matters in Indian courts, yet they remain plagued by subjectivity, delays, and inconsistencies. With over 75% of India's prison population comprising undertrial prisoners, many from socioeconomically disadvantaged backgrounds, the lack of timely and fair bail adjudication exacerbates human rights concerns and contributes to systemic judicial backlog. In this paper, we present the Indian Bail Prediction System (IBPS), an AI-powered framework designed to assist in bail decision-making by predicting outcomes and generating legally sound rationales based solely on factual case attributes and statutory provisions. We curate and release a large-scale dataset of 150,430 High Court bail judgments, enriched with structured annotations such as age, health, criminal history, crime category, custody duration, statutes, and judicial reasoning. We fine-tune a large language model using parameter-efficient techniques and evaluate its performance across multiple configurations, with and without statutory context, and with RAG. Our results demonstrate that models fine-tuned with statutory knowledge significantly outperform baselines, achieving strong accuracy and explanation quality, and generalize well to a test set independently annotated by legal experts. IBPS offers a transparent, scalable, and reproducible solution to support data-driven legal assistance, reduce bail delays, and promote procedural fairness in the Indian judicial system.

The Korean criminal justice system utilizes summary proceedings (guyaksik) to expedite high-volume minor infractions, such as simple driving under the influence (DUI), unlicensed driving, and minor traffic casualties. Although this mechanism improves judicial throughput, processing these cases creates a substantial administrative burden for prosecutors, driving the need for automated systems that can precisely translate unstructured legal text into deterministic statutory outcomes. While recent Large Language Models (LLMs) excel at semantic extraction, their probabilistic nature inherently limits their reliability in Legal Judgment Prediction tasks. Specifically, when confronted with the arithmetic constraints of legal statutes, LLMs can produce hallucinations. Given that legal accountability permits virtually no tolerance for stochastic errors, purely neural architectures remain limited in their direct judicial applications. To address these limitations, we propose a Neuro-Symbolic framework that bridges unstructured legal facts with formal verification. Our architecture restricts the LLM exclusively to semantic extraction, while offloading statutory fine calculations to a Satisfiability Modulo Theories solver. This division of labor reduces hallucination risks during computation. Furthermore, we incorporate a Human-in-the-Loop verification scheme to preserve professional legal oversight. We formalize the 2026 Sentencing Guidelines for Traffic Offenses within this pipeline, demonstrating a deterministic approach to supporting summary indictments.

Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the note fails to record. The standard check is an LLM judge: a second model reads the note against the transcript and flags problems. We ask whether judges detect omissions. Public corpora cannot supply the answer key: their clinician reference notes and transcripts are materially discrepant. Our benchmark has 500 single-error note pairs from audited fact sheets, 298 with a named fact certainly absent and 202 added-or-altered controls. Across eight judge designs, paired discrimination (the flawed note below its clean twin, 0.5 a coin flip) reads 0.79-0.94 on added or altered content and 0.50-0.63 on omissions. On single notes, no design flags omissions reliably more often than perfect notes. Wording changes, voting and GEPA prompt optimisation move the operating point without creating usable detection. Restructuring the task recovers it: list the facts the transcript establishes, then check the note for each. Two methods reach it independently and trade off: a per-fact pipeline, and a GEPA-evolved prompt doing the same in one call. The pipeline's flags name the missing fact and its severity at 2.7% false alarms. The single call detects more (36.9% against 24.6%, p=0.002) at 6.2% false alarms and a tenth of the cost per note. A physician author validated 70 items and, where the two routes disagree, sided with the pipeline on 10 of 10 (p=0.002). A second clinician, not an author, graded the severity rubric blind and agrees to within a grade. On real vendor notes from a companion census no benchmark threshold transfers, but the re-calibrated single call detects more than the best of the eight at half its false-alarm rate. Omissions whose fact is restated elsewhere defeat both routes. We release the benchmark, prompts and judgements.

Large language models (LLMs) demonstrate considerable potential in various natural language tasks but face significant challenges in mathematical reasoning, particularly in executing precise, multi-step logic. However, current evaluation frameworks judge their performance solely based on accuracy, which only accounts for the final answer. This study explores these pitfalls by employing a novel evaluation framework. We propose an evaluation metric called the MAPLE score, which holistically quantifies reasoning misalignment by integrating error rates, redundancy, and validity.

Evaluation for automatic crisis reporting should measure what practitioners need, not what is convenient to compare. Through LLM-assisted, author-approved content analysis, we derive a 15-slot information schema from professional humanitarian situation reports using qualitative content analysis, then evaluate 121 human and 261 LLM-generated reports across five disasters and three hazard types. Under google/gemini-3.7-flash on Cyclone Idai, the best machine arm is nominally above the empirical human ceiling (0.827 vs. 0.821), but the difference is statistically indistinguishable from zero (95\% bootstrap CI [-.049,.059]; permutation p=.852), and the ordering does not replicate under openai/gpt-5.6-luna. On a blind 100-item Idai sample, the author agrees with the Gemini judge at 0.910 accuracy and unweighted Cohen's κ=.799. All four judges clear the plan's raw-agreement criterion of .7; only Gemini reaches .7 on chance-corrected κ. Across the three primary events, machine reports reproduce 5.4-11.0% of same-day official figures. Across those same events, raw exact-number matching links 14.3-19.6% of official figures and 85.4-90.1% of machine figures to the social stream; manual audit confirms 45/50 declared absences, 4/25 official matches, and 24/25 machine matches semantically. The issuing-provenance gap is positive in all 12 observed event-judge cells: report date, organisation, series, and authority were not supplied at professional-report coverage in any cell. On the three primary events, ROUGE-L is uninformative, BERTScore is negatively associated with completeness after multiplicity correction, and a generic LLM judge changes sign.

Standard supervised fine-tuning (SFT) assigns the same explicit loss weight to every expert demonstration, regardless of the model's changing competence over training queries. Reinforcement learning (RL) based methods adapt update strength using model-generated rollouts, but often require substantially more sampling and can be unstable on hard tasks. We propose Online Self-Weighted Fine-Tuning (OSW-FT), a simple method that augments SFT with online, trajectory-level weighting. For each query, OSW-FT estimates the model's current success rate using a small number of inference-only rollouts and rescales the standard SFT loss accordingly. The optimization direction remains anchored to the expert trajectory, while the update magnitude adapts online. For binary-verifiable reasoning, we connect this weighting to SFT and RL at the gradient level, inspired by variance-reduction principles. The resulting estimator is unbiased for the exact OSW-FT surrogate update for any finite rollout count, and we analyze convergence with respect to the corresponding surrogate objective. Evaluated across Qwen3 series ranging from 0.6B to 4B on multiple challenging benchmarks (e.g., AIME), OSW-FT consistently improves over SFT on small-to-medium scale models. OSW-FT offers a favorable compute-performance trade-off as a practical approach for fine-tuning small-to-medium LLMs on binary-verifiable reasoning tasks with only 2 online rollouts.

A sound judgment applies the law to established facts and weighs the circumstances in which they arose. However, existing methods swing between rigid statute matching and ungrounded discretion, benchmarks score a label or a rubric, and the experience that would supply the balance stays unverified. We formalize legal judgment as a reference-anchored task, whose object is a single decision that stays tied to the statute and to the circumstances at once. We introduce JusticeAxis, 256 real-world criminal cases from 18 countries with audio, image, and text evidence, and three lawyer-written judgments for every case: the recorded one and one for each failure. We further propose JusticeAgent, a harness whose element agents establish the facts and whose judge agent applies the law under skills carrying experience of the circumstances. Skills are distilled from execution trajectories and admitted only under Bayesian credible bounds. Experiments show that failure turns direction with scale: open-weight backbones drift to unsupported grounds, frontier models to the statutory default. We further verify that JusticeAgent, as a simple yet effective plugin, carries a frozen open-weight backbone to commercial level. Project resources are available at https://github.com/beita6969/JusticeAxis.

The rapid deployment of AI systems in high-stakes domains, including those classified as high-risk under the The EU AI Act (Regulation (EU) 2024/1689), has intensified the need for reliable compliance auditing. For binary classifiers, regulatory risk assessment often relies on global fairness metrics such as the Disparate Impact ratio, widely used to evaluate potential discrimination. In typical auditing settings, the auditee provides a subset of its dataset to an auditor, while a supervisory authority may verify whether this subset is representative of the full underlying distribution. In this work, we investigate to what extent a malicious auditee can construct a fairness-compliant yet representative-looking sample from a non-compliant original distribution, thereby creating an illusion of fairness. We formalize this problem as a constrained distributional projection task and introduce mathematically grounded manipulation strategies based on entropic and optimal transport projections. These constructions characterize the minimal distributional shift required to satisfy fairness constraints. To counter such attacks, we formalize representativeness through distributional distance based statistical tests and systematically evaluate their ability to detect manipulated samples. Our analysis highlights the conditions under which fairness manipulation can remain statistically undetected and provides practical guidelines for strengthening supervisory verification. We validate our theoretical findings through experiments on standard tabular datasets for bias detection. Code is publicly available at https://github.com/ValentinLafargue/Inspection.

The use of LLMs as automated judges ("LLM-as-a-judge") is now widespread, yet standard judges suffer from a multitude of reliability issues. To address these challenges, we introduce Verdict, an open-source library for scaling judge-time compute to enhance the accuracy, reliability, and interpretability of automated evaluators. Verdict leverages the composition of modular reasoning units (such as verification, debate, and aggregation) and increased inference-time compute to improve LLM judge quality. Across a variety of challenging tasks such as content moderation, fact-checking, and hallucination detection, Verdict judges achieves performance competitive with orders-of-magnitude larger fine-tuned judges, prompted judges, and reasoning models. Our framework establishes a foundation for scalable, interpretable, and reliable LLM-based evaluation systems for both researchers and practitioners.

In the landscape of Fact-based Judgment Prediction and Explanation (FJPE), reliance on factual data is essential for developing robust and realistic AI-driven decision-making tools. This paper introduces TathyaNyaya, the largest annotated dataset for FJPE tailored to the Indian legal context, encompassing judgments from the Supreme Court of India and various High Courts. Derived from the Hindi terms "Tathya" (fact) and "Nyaya" (justice), the TathyaNyaya dataset is uniquely designed to focus on factual statements rather than complete legal texts, reflecting real-world judicial processes where factual data drives outcomes. Complementing this dataset, we present FactLegalLlama, an instruction-tuned variant of the LLaMa-3-8B Large Language Model (LLM), optimized for generating high-quality explanations in FJPE tasks. Finetuned on the factual data in TathyaNyaya, FactLegalLlama integrates predictive accuracy with coherent, contextually relevant explanations, addressing the critical need for transparency and interpretability in AI-assisted legal systems. Our methodology combines transformers for binary judgment prediction with FactLegalLlama for explanation generation, creating a robust framework for advancing FJPE in the Indian legal domain. TathyaNyaya not only surpasses existing datasets in scale and diversity but also establishes a benchmark for building explainable AI systems in legal analysis. The findings underscore the importance of factual precision and domain-specific tuning in enhancing predictive performance and interpretability, positioning TathyaNyaya and FactLegalLlama as foundational resources for AI-assisted legal decision-making.

Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally blind to whether a formal translation maintains strict reference-equivalence to a designated formalization. We formalize this vulnerability as Verdict-Preserving-Unfaithfulness (VPU): a failure mode where an incorrect encoding executes successfully and matches the expected verdict. We theoretically prove that structural, verdict-only verification heuristics are mathematically bounded to chance-level detection on these deceptively valid traces. To resolve this, we introduce Generative Verification (GenV), which distills an offline Z3-equivalence oracle into a reference-free, continuous reference-equivalence score by repurposing the language model's native vocabulary space. Mechanistic analysis via decision-projected logit lenses and sparse autoencoders shows this generative readout natively extracts precise spatial error coordinates without explicit localization training. Empirically, our oracle-mined verifier (GenV+HN) achieves 0.961 AUROC in reference-equivalence verification, generalizes zero-shot across unseen translators and divergent formal styles, and yields an 11.3-point downstream accuracy gain in agentic test-time compute allocation.

Given the challenge of automatically evaluating free-form outputs from large language models (LLMs), an increasingly common solution is to use LLMs themselves as the judging mechanism, without any gold-standard scores. Implicitly, this practice accounts for only sampling variability (aleatoric uncertainty) and ignores uncertainty about judge quality (epistemic uncertainty). While this is justified if judges are perfectly accurate, it is unclear when such an approach is theoretically valid and practically robust. We study these questions for the task of ranking LLM candidates from a novel geometric perspective: for M-level scoring systems, both LLM judges and candidates can be represented as points on an (M-1)-dimensional probability simplex, where geometric concepts (e.g., triangle areas) correspond to key ranking concepts. This perspective yields intuitive theoretical conditions and visual proofs for when rankings are identifiable; for instance, we provide a formal basis for the ``folk wisdom'' that LLM judges are more effective for two-level scoring (M=2) than multi-level scoring (M>2). Leveraging the simplex, we design geometric Bayesian priors that encode epistemic uncertainty about judge quality and vary the priors to conduct sensitivity analyses. Experiments on LLM benchmarks show that rankings based solely on LLM judges are robust in many but not all datasets, underscoring both their widespread success and the need for caution. Our Bayesian method achieves substantially higher coverage rates than existing procedures, highlighting the importance of modeling epistemic uncertainty.

Multi-constraint instruction following requires verifying whether a response satisfies multiple individual requirements, yet LLM judges are often assessed only through overall-response judgments. We introduce MCJudgeBench, a benchmark for constraint-level judge evaluation in multi-constraint instruction following. Each instance includes an instruction, a candidate response, an explicit constraint list, per-constraint gold labels in {yes, partial, no}, and controlled response-side perturbations. The evaluation protocol further includes evaluation prompt variants to test judge stability. We evaluate proprietary and open-source LLM judges using both correctness and inconsistency metrics, distinguishing intrinsic inconsistency under stochastic decoding from procedural inconsistency under prompt and response perturbations. Our results show that judge reliability has multiple dimensions: strong overall performance does not guarantee equally reliable detection across label categories, especially for rarer partial and no cases. Judges with higher correctness do not always have lower inconsistency. Evaluation with reasoning improves correctness but does not uniformly improve stability. These findings motivate evaluating LLM judges at the constraint level to study these failure modes.

Mathematical reasoning models are widely deployed in education, automated tutoring, and decision support systems despite exhibiting fundamental computational instabilities. We demonstrate that state-of-the-art models (Qwen2.5-Math-7B) achieve 61% accuracy through a mixture of reliable and unreliable reasoning pathways: 18.4% of correct predictions employ stable, faithful reasoning while 81.6% emerge through computationally inconsistent pathways. Additionally, 8.8% of all predictions are silent failures -- confident yet incorrect outputs. Through comprehensive analysis using novel faithfulness metrics, we reveal: (1) reasoning quality shows weak negative correlation with correctness (r=-0.21, p=0.002), reflecting a binary classification threshold artifact rather than a monotonic inverse relationship; (2) scaling from 1.5B to 7B parameters (4.7x increase) provides zero accuracy benefit on our evaluated subset (6% of GSM8K), requiring validation on the complete benchmark; and (3) latent reasoning employs diverse computational strategies, with ~20% sharing CoT-like patterns. These findings highlight that benchmark accuracy can mask computational unreliability, demanding evaluation reforms measuring stability beyond single-sample metrics.

Benchmarks for LLM-generated GPU kernels (KernelBench, TritonBench, GEAK) score correctness through fixed-shape, small-sample allclose-style checks. The number of inputs varies between benchmarks. The shape, dtype, and tolerance are fixed for each kernel. We test that oracle empirically. We construct a controlled corpus of 24 Triton and CPU stand-in kernels (15 correct controls and 9 LLM-style buggy variants seeded with documented transcription errors) and re-evaluate it under op-schema-aware seeded fuzzing with a high-precision (fp64) CPU reference and per-(op, dtype) absolute tolerances. The seeded oracle flags 9 of 9 buggy kernels and passes 15 of 15 correct controls, at zero precision cost on controls. We extend the corpus to 26 ops (adding a flash-attention pair) and re-run the same protocol on five GPU classes (RTX 3060, A10, L40S, A100 SXM4, H100 NVL). The verdicts are identical across all five GPUs: 10 of 10 illusions caught and 16 of 16 controls clean. The corpus result is about LLM-style transcription bugs that the allclose-on-one-shape oracle certifies as correct, not about the bug rate of any specific deployed LLM. Every flagged failure replays byte-for-byte from a stored seed.

The rapid advancement of artificial intelligence in legal natural language processing demands scalable methods for evaluating text extraction from judicial decisions. This study evaluates 16 unsupervised metrics, including novel formulations, to assess the quality of extracting seven semantic blocks from 1,000 anonymized Russian judicial decisions, validated against 7,168 expert reviews on a 1--5 Likert scale. These metrics, spanning document-based, semantic, structural, pseudo-ground truth, and legal-specific categories, operate without pre-annotated ground truth. Bootstrapped correlations, Lin's concordance correlation coefficient (CCC), and mean absolute error (MAE) reveal that Term Frequency Coherence (Pearson r = 0.540, Lin CCC = 0.512, MAE = 0.127) and Coverage Ratio/Block Completeness (Pearson r = 0.513, Lin CCC = 0.443, MAE = 0.139) best align with expert ratings, while Legal Term Density (Pearson r = -0.479, Lin CCC = -0.079, MAE = 0.394) show strong negative correlations. The LLM Evaluation Score (mean = 0.849, Pearson r = 0.382, Lin CCC = 0.325, MAE = 0.197) showed moderate alignment, but its performance, using gpt-4.1-mini via g4f, suggests limited specialization for legal textse. These findings highlight that unsupervised metrics, including LLM-based approaches, enable scalable screening but, with moderate correlations and low CCC values, cannot fully replace human judgment in high-stakes legal contexts. This work advances legal NLP by providing annotation-free evaluation tools, with implications for judicial analytics and ethical AI deployment.

Fine-tuning large language models (LLMs) on reasoning benchmarks via reinforcement learning requires a specific reward function, often binary, for each benchmark. This comes with two potential limitations: the need to design the reward, and the potentially sparse nature of binary rewards. Here, we systematically investigate rewards derived from the probability or log-probability of emitting the reference answer (or any other prompt continuation present in the data), which have the advantage of not relying on specific verifiers and being available at scale. Several recent works have advocated for the use of similar rewards (e.g., VeriFree, JEPO, RLPR, NOVER). We systematically compare variants of likelihood-based rewards with standard baselines, testing performance both on standard mathematical reasoning benchmarks, and on long-form answers where no external verifier is available. We find that using the log-probability of the reference answer as the reward for chain-of-thought (CoT) learning is the only option that performs well in all setups. This reward is also consistent with the next-token log-likelihood loss used during pretraining. In verifiable settings, log-probability rewards bring comparable or better success rates than reinforcing with standard binary rewards, and yield much better perplexity. In non-verifiable settings, they perform on par with SFT. On the other hand, methods based on probability, such as VeriFree, flatline on non-verifiable settings due to vanishing probabilities of getting the correct answer. Overall, this establishes log-probability rewards as a viable method for CoT fine-tuning, bridging the short, verifiable and long, non-verifiable answer settings.

Pass@k is widely used to report the reasoning performance of LLMs, but it often produces unstable and potentially misleading rankings, especially when the number of trials (samples) is limited and computational resources are constrained. We present a principled Bayesian evaluation framework that replaces Pass@k and average accuracy over N trials (avg@N) with posterior estimates of a model's underlying success probability and credible intervals, yielding stable rankings and a transparent decision rule for differences. Evaluation outcomes are modeled as categorical (not just 0/1) with a Dirichlet prior, giving closed-form expressions for the posterior mean and uncertainty of any weighted rubric and enabling the use of prior evidence when appropriate. Theoretically, under a uniform prior, the Bayesian posterior mean is order-equivalent to average accuracy (Pass@1), explaining its empirical robustness while adding principled uncertainty. Empirically, in simulations with known ground-truth success rates and on AIME'24/'25, HMMT'25, and BrUMO'25, the posterior-based procedure achieves faster convergence and greater rank stability than Pass@k and recent variants, enabling reliable comparisons at far smaller sample counts. The framework clarifies when observed gaps are statistically meaningful (non-overlapping credible intervals) versus noise, and it naturally extends to graded, rubric-based evaluations. Together, these results recommend replacing Pass@k for LLM evaluation and ranking with a posterior-based, compute-efficient protocol that unifies binary and non-binary evaluation while making uncertainty explicit. Source code is available at https://github.com/mohsenhariri/scorio

Background: AI-powered code generation, fueled by Large Language Models (LLMs), is revolutionizing software development. Models like OpenAI's Codex and GPT-4, alongside DeepSeek, leverage vast code and natural language datasets. However, ensuring code quality, correctness, and managing complex tasks remains challenging, necessitating thorough evaluation. Methodology: This research compares ChatGPT (version o1) and DeepSeek (version R1) for Python code generation using online judge coding challenges. It evaluates correctness (online judge verdicts, up to three attempts), code quality (Pylint/Flake8), and efficiency (execution time/memory usage). Results: DeepSeek demonstrated higher correctness, particularly on algorithmic tasks, often achieving 'Accepted' on the first attempt. ChatGPT sometimes requires multiple attempts or failures. ChatGPT encountered fewer issues, used comparable or slightly less memory, consumed less execution times and wrote fewer lines of code. Conclusion: DeepSeek exhibited superior correctness in Python code generation, often requiring fewer attempts, suggesting an advantage in algorithmic problem-solving. Both models showed almost similar efficiency in execution time and memory use. Finally, this research provides insights for developers choosing AI coding assistants and informs future AI-driven software development research.

Candidate-scoring decision models return a probability distribution over a presented set of answers. Public documentation of one such system, Jev, and of an open counterpart, JevAny, describes three training ingredients that determine what these probabilities estimate: soft targets from larger models, a frozen pretrained backbone and temperature calibration. We analyze each ingredient in Gaussian surrogates where the finite-sample risk can be computed exactly. A student trained on teacher targets inherits the teacher's bias, which more student data does not remove and agreement with the teacher does not reveal. A fixed representation lowers the risk only below an explicit sample-size threshold. In a probit model the exact recalibration map is a temperature scaling, which removes all excess risk only when the teacher's coefficient has the correct direction and otherwise leaves a residual that calibration diagnostics do not detect. Under Luce's choice axiom, candidate scores are coherent across refinements of an event if and only if they aggregate by log-sum-exp. On 231,521 credit card complaints from the Consumer Financial Protection Bureau, where the decision is whether a complaint ends in monetary relief, a student trained on a logistic teacher's probabilities ends at the teacher's decision cost while a student trained on outcomes goes 8% below it, a 30B model read zero-shot remains worse than the teacher after recalibration, and that model departs from the coherence condition by 17.5 decibans. Pretrained representations reduce the labeled data required and calibration corrects the scale of the probabilities, but neither corrects a biased teacher, so the probabilities have to be checked against realized outcomes.

Commonly used evaluation measures including Recall, Precision, F-Measure and Rand Accuracy are biased and should not be used without clear understanding of the biases, and corresponding identification of chance or base case levels of the statistic. Using these measures a system that performs worse in the objective sense of Informedness, can appear to perform better under any of these commonly used measures. We discuss several concepts and measures that reflect the probability that prediction is informed versus chance. Informedness and introduce Markedness as a dual measure for the probability that prediction is marked versus chance. Finally we demonstrate elegant connections between the concepts of Informedness, Markedness, Correlation and Significance as well as their intuitive relationships with Recall and Precision, and outline the extension from the dichotomous case to the general multi-class case.

Credit risk modeling relies extensively on Weight of Evidence (WoE) and Information Value (IV) for feature engineering, and Population Stability Index (PSI) for drift monitoring, yet their theoretical foundations remain disconnected. We establish a unified information-theoretic framework revealing these industry-standard metrics as instances of classical information divergences. Specifically, we prove that IV exactly equals PSI (Jeffreys divergence) computed between good and bad credit outcomes over identical bins. Through the delta method applied to WoE transformations, we derive standard errors for IV and PSI, enabling formal hypothesis testing and probabilistic fairness constraints for the first time. We formalize credit modeling's inherent performance-fairness trade-off as maximizing IV for predictive power while minimizing IV for protected attributes. Using automated binning with depth-1 XGBoost stumps, we compare three encoding strategies: logistic regression with one-hot encoding, WoE transformation, and constrained XGBoost. All methods achieve comparable predictive performance (AUC 0.82-0.84), demonstrating that principled, information-theoretic binning outweighs encoding choice. Mixed-integer programming traces Pareto-efficient solutions along the performance-fairness frontier with uncertainty quantification. This framework bridges theory and practice, providing the first rigorous statistical foundation for widely-used credit risk metrics while offering principled tools for balancing accuracy and fairness in regulated environments.

Large language models (LLMs) increasingly decide whether software behaves correctly, either by writing a test oracle or by acting as one. Yet two oracles can look identical and rest on different ground: one assertion encodes a written specification, another only what the model learned in training. Prior secondary studies sort oracles by form or by technique, rarely by the property that governs how far a verdict can be trusted: where its authority comes from. This systematic literature review, reported under the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, screens 2,436 records to 54 included studies, extended by citation searching (snowballing) to 83 in total. We read the corpus along three axes: the source of an oracle's authority, the form it takes, and the mechanism that adjudicates it. Just over half of the corpus reaches a verdict with no specification at all. That is what lets these oracles work on code with no specification to consult, and what leaves a challenged verdict with less to fall back on. Source and mechanism cross-cut rather than coincide, so a label such as LLM-as-a-judge names how a verdict is produced, not why it should be trusted. Oracle quality is most often judged by resemblance to a known oracle rather than by whether injected faults are caught. The first question to ask of any LLM oracle is therefore what one would point to in defending its verdict. The protocol, search query, and per-study coding sheet are released.

Jailbreak robustness has become central to large language model (LLM) safety evaluation, yet prevailing methodologies rely primarily on refusal behavior, semantic resemblance, and intent-matching heuristics that emphasize linguistic plausibility rather than correctness. We identify a key limitation in existing evaluations: many jailbreak intents depend on instructional validity rather than epistemic factuality, allowing realistic-looking responses to be labeled successful despite being factually or procedurally incorrect. To address this gap, we propose Sequential Epistemic and Action-Level Validation (SEAV), a verification-centric jailbreak evaluation framework that decomposes responses into ordered steps and evaluates both validity and correctness. SEAV combines LLM-as-a-judge mechanisms for semantic interpretation with retrieval-grounded verification using external knowledge sources, assessing whether generated content is factually correct, structurally consistent, and operationally capable of advancing harmful objectives. Empirically, SEAV cuts the false-positive rate on SD-A (a curated strategic-dishonesty diagnostic) by 14.9\,pp vs. the strongest baseline, and reclassifies 22.1\%--51.0\% of sampled prior-labeled successes as invalid across three of four public benchmarks. Together, these results show that enforcing correctness substantially reshapes measured robustness: many previously labeled jailbreak successes are reclassified as invalid, and results are stable across the tested search backends and evaluator models. Code and data are available at https://github.com/Ardor-Wu/SEAV.

Common evaluation paradigms for language models focus on scoring single responses through accuracy metrics or proper scoring rules, failing to capture the full richness of a model's belief state. Recent work illustrates that language models hallucinate in-part because they are optimised to be good test-takers under binary scoring schemes that reward any answer over abstention. While this insight naturally leads to penalty-based approaches, they ignore crucial distinctions in how models distribute uncertainty, for example between hedging toward incorrect answers versus hedging toward "I don't know" responses. A novel evaluation metric, the Distributional Correctness Score (DCS), is introduced to solve this problem, i.e., of not considering a model's entire probability distribution over answer choices. DCS naturally distinguishes between harmful overconfidence in wrong answers and uncertainty expressed through abstention, providing scores in an interpretable default range. Through theoretical analysis and illustrative examples, DCS is demonstrated to offer a more nuanced and aligned evaluation paradigm that incentivises models to express genuine uncertainty rather than guessing. Adapting 12 existing evaluation benchmarks to DCS's variants and measuring performance on six language models reveals that for half of the tested benchmarks scores are negative across all tested models, indicating significant tendencies towards hallucination.

Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundant symbols, then route users through disguised links to services associated with pornography, fraud, gambling, or illicit transactions. Existing benchmarks evaluate obfuscated text and risky webpages separately, obscuring how target recovery affects downstream evidence acquisition. We introduce RiskChainBench, pairing 3,600 synthetic token-text restoration inputs from 600 source sessions with 600 corresponding human-labeled local web environments. A model first restores the message, operational intent, and destination; the same underlying model then acts as a VLM-driven web agent that investigates the correctly associated website and produces a frozen, evidence-cited risk report without message-side semantics or domain-reputation cues. We score restoration and correct-routing web investigation separately and compose them offline by applying the frozen primary-entry prediction as a gate to the same Task 2 result. Human labels determine task correctness, while a fixed multimodal evidence judge assesses faithfulness, sufficiency, completeness, and consistency. Across ten models, Entry Top-1 ranges from 35.2% to 95.2% and web decision accuracy from 26.3% to 62.8%; the leading systems differ across entry recovery, full reconstruction, website decisions, and fine-grained typing. Execution failures account for 31.9% of web runs, whereas post-decision type errors account for only 0.9%, identifying stable exploration and risk judgment as the principal bottlenecks. We release the benchmark, protocol, and resettable local sandbox.

LLM-as-a-judge enables evaluation across diverse tasks, but inference cost and confidence reliability become critical at scale. We study whether a decision-only judge can provide an economical first pass and identify when stronger evaluation is needed. Comparing jev-as-a-judge with sixteen generative and reward-model judges, with blinded human adjudication, we find it within three percentage points of a state-of-the-art LLM judge, our strongest comparator, on ordinary preference and evidence-grounded factuality at 0.36% of the comparator's fee. Larger gaps arise when judgments require checking a derivation or resisting an elaborately written wrong answer. On several benchmarks, JEV's gap to this comparator is concentrated in low-confidence decisions. A frozen cascade that accepts confident verdicts and escalates uncertain ones retains 99% of the comparator's accuracy at lower cost.

Generative reward models (GenRMs) generate natural language rationales to justify preference judgments, yet a correct verdict does not guarantee a sound justification. Existing approaches often rely on reference explanations to supervise rationales, but obtaining such references can be costly and does not necessarily establish whether generated rationales support the resulting verdict. To address these limitations, we propose DeCert, a framework that evaluates the validity and verdict consistency of generated rationales without requiring reference explanations. Crucially, DeCert translates these assessments into preference supervision that accounts for both verdict correctness and justification quality. In particular, when multiple sampled judgments share the same correct verdict, differences in certificate quality enable DeCert to construct rationale preference pairs that distinguish stronger from weaker justifications. Extensive empirical studies across two model families and multiple in- and out-of-distribution benchmarks demonstrate that DeCert consistently outperforms strong generative judge baselines while improving rationale quality. Moreover, DeCert effectively mitigates positional bias, improving position-consistent accuracy by up to 14.8 points. These results highlight the importance of supervising not only which verdict is correct, but also how that verdict is justified.

Retrieval-augmented generation asks one question at volume: does this evidence support this claim? The answer is one bit, yet most pipelines obtain it from a text generator and pay generation prices for the prose wrapped around it. We compare a non-generative decision model, which returns a typed value from a declared enumeration together with a native probability and no text, against a frontier LLM configured as an engineer would deploy it for binary classification. Both answer the same 495 human-labelled claims from LLM-AggreFact, so every comparison is within-item. We report three things. First, the two systems are statistically indistinguishable on the metric this task is conventionally scored by, a paired difference of -0.56 points, Jev minus Astra, at a 187-fold cost difference. Second, that tie carries almost no information about deployment: the systems disagree on 15.2% of claims, and the cheaper one admits 23.2% of the claims annotators marked unsupported against the frontier model's 14.1%. A component whose job is to catch unsupported claims should be judged on that rate, and the conventional headline hides it. Third, because the errors differ they compose: routing the claims the cheap model is confident about and escalating the rest reaches 74.10 at USD 2.92 per thousand claims against 73.83 at USD 8.93, with the threshold chosen out of fold. But a matched random-escalation control at in-sample thresholds, spending the same budget by coin flip, does as well, so what buys the saving is the escalation share and not the probability that picks what to escalate. Measured against the cheap model it is built from, the cascade costs 61-fold more for 0.83 points, 95% CI [-3.36, 4.86], and it is the more permissive guard of the two. Equal accuracy conceals unequal errors. All predictions, prompts, pricing and code are released.

The integration of artificial intelligence (AI) into judicial decision making -- particularly in pretrial, sentencing, and parole contexts -- has generated a substantial and rapidly growing literature. Across computer science, economics, law, criminology, and psychology, researchers have examined the reliability, fairness, and real-world effects of AI-assisted decision making. Yet this literature remains fragmented, and differences in assumptions, concepts, and research priorities make it difficult to assess what is actually known. Using criminal justice risk assessment as a focal case, this article makes two contributions. First, we develop a conceptual framework that distinguishes and relates three central questions: (1) the predictive validity of automated risk assessment tools; (2) how algorithmic risk assessments compare with human predictions (AI-versus-Human); and (3) how algorithmic recommendations affect judges' decisions (AI-plus-Human). Second, we use this framework to synthesize the empirical evidence addressing each of these questions. Our review identifies important limitations in existing research on predictive validity, as well as substantial gaps in understanding how judges respond to AI advice and how those responses vary across individuals and decision-making environments. The available evidence suggests that AI decision aids have, so far, had at most modest effects on pretrial and sentencing decisions. We conclude that further research is needed to understand how judges make decisions in noisy informational environments and under what conditions AI tools can produce meaningful improvements in judicial decision making.

Synthetic insider threat benchmarks face a consistency problem: corpora generated without an external factual constraint cannot rule out cross-artifact contradictions. The CERT dataset -- the field's canonical benchmark -- is also static, lacks cross-surface correlation scenarios, and predates the LLM era. We present OrgForge-IT, a verifiable synthetic benchmark in which a deterministic simulation engine maintains ground truth and language models generate only surface prose, making cross-artifact consistency an architectural guarantee. The corpus spans 51 simulated days, 2,904 telemetry records at a 96.4% noise rate, and four detection scenarios designed to defeat single-surface and single-day triage strategies across three threat classes and eight injectable behaviors. A ten-model leaderboard reveals several findings: (1) triage and verdict accuracy dissociate - eight models achieve identical triage F1=0.80 yet split between verdict F1=1.0 and 0.80; (2) baseline false-positive rate is a necessary companion to verdict F1, with models at identical verdict accuracy differing by two orders of magnitude on triage noise; (3) victim attribution in the vishing scenario separates tiers - Tier A models exonerate the compromised account holder while Tier B models detect the attack but misclassify the victim; (4) rigid multi-signal thresholds structurally exclude single-surface negligent insiders, demonstrating the necessity of parallel, threat-class-specific triage pipelines; and (5) agentic software-engineering training acts as a force multiplier for multi-day temporal correlation, but only when paired with frontier-level parameter scale. Finally, prompt sensitivity analysis reveals that unstructured prompts induce vocabulary hallucination, motivating a two-track scoring framework separating prompt adherence from reasoning capability. OrgForge-IT is open source under the MIT license.

LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling. Judges are typically validated by accuracy on golden data, but accuracy says little about whether they are stable under re-prompting, challenge, or sustained pushback. We introduce the Wiggle Framework, a unified stress test for epistemic stability in LLM judges. The framework decomposes judge robustness along three dimensions: Mechanical Consistency (stability under re-prompting and reframing), Single-turn Conviction (stability under a single challenge), and Multi-turn Persistence (stability under sustained or adaptive pressure). We use the framework to study 9 frontier models across 14 judging tasks spanning safety, toxicity, AI writing detection, and political-response evaluation. Every model exhibits substantial wiggle as a judge --- flipping verdicts 25--71\% of the time under static pushback, and 62--91\% with an adversarial LLM persuader. Critically, we find that pressure that succeeds in changing a judge's verdict is almost always net-corrupting with respect to ground truth. Beyond the framework itself, we identify baseline jury majority strength as the most effective single-shot signal for anticipating which items wiggle. Taken together, this is the first apples-to-apples cross-dataset comparison of mechanical, conformity, and persuadability tests in a judging context.

We introduce Legal RAG Bench, a benchmark and evaluation methodology for assessing the end-to-end performance of legal RAG systems. As a benchmark, Legal RAG Bench consists of 4,876 passages from the Victorian Criminal Charge Book alongside 100 complex, hand-crafted questions demanding expert knowledge of criminal law and procedure. Both long-form answers and supporting passages are provided. As an evaluation methodology, Legal RAG Bench leverages a full factorial design and novel hierarchical error decomposition framework, enabling apples-to-apples comparisons of the contributions of retrieval and reasoning models in RAG. We evaluate three state-of-the-art embedding models (Isaacus' Kanon 2 Embedder, Google's Gemini Embedding 001, and OpenAI's Text Embedding 3 Large) and two frontier LLMs (Gemini 3.1 Pro and GPT-5.2), finding that information retrieval is the primary driver of legal RAG performance, with LLMs exerting a more moderate effect on correctness and groundedness. Kanon 2 Embedder, in particular, had the largest positive impact on performance, improving average correctness by 17.5 points, groundedness by 4.5 points, and retrieval accuracy by 34 points. We observe that many errors attributed to hallucinations in legal RAG systems are in fact triggered by retrieval failures, concluding that retrieval sets the ceiling for the performance of many modern legal RAG systems. We document why and how we built Legal RAG Bench alongside the results of our evaluations. We also openly release our code and data to assist with reproduction of our findings.

When should an AI system's answer be trusted? Formal proof assistants offer certainty but cannot reach most of the problem distribution; scalar LLM judges offer coverage but produce opaque scores that cannot be audited after the fact and are subject to the same coherence issues as any LLM. We present Theoria, a verification architecture that closes this gap. A candidate solution is rewritten into a sequence of typed state transitions, each licensed by an explicit justification, whether that be a citation, computation, or problem-given fact, and every transition is independently auditable. The foundational invariant is completeness of change: every difference between consecutive proof states must be accounted for, so hidden premises surface as unlicensed mutations rather than passing silently. On HLE-Verified Gold (185 text-only expert problems), Theoria certifies 105 at 91.4% strict precision (Wilson 95% CI [84.5%, 95.4%]). Every certification produces a human readable proof trace in which each step can be independently challenged. Holistic LLM judges achieve comparable precision at matched coverage but fail on different problems (Jaccard 0.14-0.36), making the approaches complementary. On 95 adversarial poisoned proofs across 15 domains, structured judges catch 94.7% versus 83.2% for holistic judging (p= 0.0017). The overall 11.5 pp gap concentrates in hidden premises (90.6% vs. 62.5%, a 28 pp difference) and fabricated citations (100% vs. 90%), the error classes where the formal analysis predicts an advantage; performance is identical on arithmetic and theorem-misapplication errors, where no advantage is predicted. On GPQA Diamond (n= 65), certified precision is 97.1% (Wilson CI [85.1%, 99.5%]).

In legal decisions, split votes (SV) occur when judges cannot reach a unanimous decision, posing a difficulty for lawyers who must navigate diverse legal arguments and opinions. In high-stakes domains, understanding the alignment of perceived difficulty between humans and AI systems is crucial to build trust. However, existing NLP calibration methods focus on a classifier's awareness of predictive performance, measured against the human majority class, overlooking inherent human label variation (HLV). This paper explores split votes as naturally observable human disagreement and value pluralism. We collect judges' vote distributions from the European Court of Human Rights (ECHR), and present SV-ECHR, a case outcome classification (COC) dataset with SV information. We build a taxonomy of disagreement with SV-specific subcategories. We further assess the alignment of perceived difficulty between models and humans, as well as confidence- and human-calibration of COC models. We observe limited alignment with the judge vote distribution. To our knowledge, this is the first systematic exploration of calibration to human judgements in legal NLP. Our study underscores the necessity for further research on measuring and enhancing model calibration considering HLV in legal decision tasks.

Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug. We propose BINEVAL, a framework that decomposes evaluation criteria into atomic binary questions and aggregates the resulting verdicts into interpretable, multi-dimensional scores. Given a task prompt, a meta-prompt generates fine-grained evaluation questions, and an LLM answers them independently for each output, yielding transparent question-level feedback together with calibrated overall scores. This decomposition makes evaluation easier to inspect, easier to diagnose, and directly usable for prompt improvement. Across SummEval, Topical-Chat, and QAGS, BINEVAL matches or outperforms strong baselines including UniEval and G-Eval, with especially strong results on factual consistency benchmarks such as QAGS. Beyond competitive correlation with human judgments, BINEVAL better matches human score distributions and avoids the ceiling effects common in prior LLM judges, leading to better discrimination between borderline and clearly flawed outputs. We further show that the same question-level feedback supports iterative prompt optimization, improving evaluator prompts on summarization and generation prompts on IFBench under both self-update and cross-model update settings. Overall, BINEVAL provides a task-agnostic, training-free, and interpretable evaluation framework that combines strong empirical performance with practical diagnostic and optimization value.

We propose claim-level falsification as a principle for test-time scaling and instantiate it through Claim-Level Reliability Assessment (CLR), a training-free framework that reallocates test-time compute from additional solution sampling to targeted verification. Since whole-trace evaluation often obscures decisive errors due to signal dilution from routine tokens, CLR condenses each reasoning trace into a compact set of decision-critical claims, thereby isolating its logical anchors. Furthermore, recognizing the inherent difficulty of generating entirely correct solutions under fixed model capabilities, CLR shifts the focus to semantic falsification. This approach exploits a fundamental asymmetry between solution construction and claim refutation. Constructing a valid solution requires a flawless reasoning path, whereas refuting an incorrect claim requires identifying only a single decisive flaw. This targeted search for negative evidence systematically compresses the survival space of high-confidence incorrect traces, effectively suppressing erroneous consensus via nonlinear reliability scoring. Across four LLMs and four reasoning benchmarks under matched budgets, CLR generally improves upon pass@1 and self-consistency. On GPT-OSS-20B/CMIMC25, for instance, CLR exceeds pass@1 by 27.15 percentage-points and raises self-consistency accuracy from 77.50\% to 82.19\% with 37.0\% fewer tokens.

The probabilistic reading of the cumulative accuracy profile (CAP) has a long industry lineage. Falkenstein, Boral and Carty (2000) state, in discrete form, that the default rate at a score percentile equals the portfolio average rate times the local slope of the power curve; van der Burgt (2008, 2019) formalizes this as the continuous identity p(Dmid x) = p_D, dy/dx and imports the continuous form as a working fact; Tasche (2009) analyzes the resulting calibration method; Voloshyn and Voloshyn (2023) substitute Bayes' theorem, f(xmid D)=p(Dmid x) f(x)/p_D, into the area integral and write the Gini as a functional of the calibration curve. The slope itself is already in the lineage (van der Burgt's dy/dx is the ratio of the two cumulative differentials), but it enters as a cited working fact, never as Bayes' theorem. We make that identification explicit and draw out its consequences. First, the CAP slope is Bayes' theorem in cumulative coordinates: the standardized PD it recovers is the posterior probability rescaled by the prior. The weight of the paper then falls on two results this reading unlocks. The odds form places the weight of evidence (the log of the likelihood ratio, i.e. the Bayes factor) and the information value inside one geometry (the weight of evidence at a point is the log of the ratio of the "bad" and "good" CAP slopes). The accuracy ratio, Somers' D_{xy}, and the Gini (2A-1)/(1-p_D) are revealed as one number computed three ways. Run in comparison mode (realized outcomes against model claims), the same identity recovers the reliability diagram in cumulative coordinates, with the sign of the gap between the empirical and model-implied Gini coefficients as a calibration diagnostic. A worked five-band example carries every identity in discrete form, and a kernel-density example extends them to the continuous case.

We describe our submission to the MedReason 2026 challenge, covering multiple-choice (MCQ) and open-ended (OE) medical visual question answering (VQA) under fully offline, containerized inference. Our first finding is that MCQ retrieval must compare answer semantics rather than answer labels: labels are independently assigned per question, so copying a retrieved neighbor's label transfers no useful information, whereas scoring each current option's text against correct-answer text from similar training cases raises retrieval-only accuracy from 20.0\% to 57.5\% on a 200-case retrieval-excluded development holdout. Our second finding attributes the submitted system's accuracy: holding the task-specific MCQ Low-Rank Adaptation (LoRA) adapter fixed and varying the number \(k\) of in-prompt retrieved examples changes accuracy by at most one case --- 187/200 (93.5\%) at both \(k=0\) and the adapter's training-time \(k=1\), 188/200 (94.0\%) at the packaged runtime's default \(k=3\) --- and the submitted confidence-gated override adds no net accuracy on top of \(k=3\), selecting the VLM in 198/200 cases. With the final MCQ adapter fixed, retrieval changes accuracy by at most one case, and gating provides no net gain. On 20 OE cases, token-F1 and RaTEScore~zhao2024ratescore decrease as \(k\) grows, but paired sign tests on token-F1 differences are nonsignificant (\(p \ge 0.29\)); a single-annotator comparison found 6/20 wrong-anchor errors for the final configuration and 14/20 for an earlier configuration that jointly differed in routing, adapter, and prompting. The system reaches 94.0\% MCQ accuracy on the development holdout and 93.20\% on the organizer's official pre-evaluation, versus 29.43\% for the off-the-shelf reference baseline, while both of the organizer's open-ended scores are lower than that baseline's (ground-truth agreement 1.245 versus 1.588, visual accuracy 1.995 versus 2.696, each out of 4).

Large Language Models (LLMs) are increasingly employed as automated evaluators to assess the safety of generated content, yet their reliability in this role remains uncertain. This study evaluates a diverse set of 11 LLM judge models across critical safety domains, examining three key aspects: self-consistency in repeated judging tasks, alignment with human judgments, and susceptibility to input artifacts such as apologetic or verbose phrasing. Our findings reveal that biases in LLM judges can significantly distort the final verdict on which content source is safer, undermining the validity of comparative evaluations. Notably, apologetic language artifacts alone can skew evaluator preferences by up to 98\%. Contrary to expectations, larger models do not consistently exhibit greater robustness, while smaller models sometimes show higher resistance to specific artifacts. To mitigate LLM evaluator robustness issues, we investigate jury-based evaluations aggregating decisions from multiple models. Although this approach both improves robustness and enhances alignment to human judgements, artifact sensitivity persists even with the best jury configurations. These results highlight the urgent need for diversified, artifact-resistant methodologies to ensure reliable safety assessments.

This work demonstrates that Legal Judgement Prediction systems without expert-informed adjustments can be vulnerable to shallow, distracting surface signals that arise from corpus construction, case distribution, and confounding factors. To mitigate this, we use domain expertise to strategically identify statistically predictive but legally irrelevant information. We adopt adversarial training to prevent the system from relying on it. We evaluate our deconfounded models by employing interpretability techniques and comparing to expert annotations. Quantitative experiments and qualitative analysis show that our deconfounded model consistently aligns better with expert rationales than baselines trained for prediction only. We further contribute a set of reference expert annotations to the validation and testing partitions of an existing benchmark dataset of European Court of Human Rights cases.

Large language models (LLMs) are increasingly applied as automatic evaluators for natural language generation assessment often using pairwise comparative judgements. Existing approaches typically rely on single judges or aggregate multiple judges assuming equal reliability. In practice, LLM judges vary substantially in performance across tasks and evaluation aspects, and their judgment probabilities may be biased and inconsistent. Furthermore, human-labelled supervision for judge calibration may be unavailable. We first empirically demonstrate that inconsistencies in LLM comparison probabilities exist and show that it limits the effectiveness of direct probability-based ranking. To address this, we study the LLM-asa-jury setting and propose BT-sigma, a judge-aware extension of the Bradley-Terry model that introduces a discriminator parameter for each judge to jointly infer item rankings and judge reliability from pairwise comparisons alone. Experiments on benchmark NLG evaluation datasets show that BT-sigma consistently outperforms averaging-based aggregation methods, and that the learned discriminators strongly correlate with independent measures of the cycle consistency of LLM judgments. Further analysis reveals that BT-sigma can be interpreted as an unsupervised calibration mechanism that improves aggregation by modelling judge reliability.

We propose a general two-stage algorithm that enjoys a provable scaling law for the test-time compute of large language models (LLMs). Given an input problem, the proposed algorithm first generates N candidate solutions, and then chooses the best one via a multiple-round knockout tournament where each pair of candidates are compared for K times and only the winners move on to the next round. In a minimalistic implementation, both stages can be executed with a black-box LLM alone and nothing else (e.g., no external verifier or reward model), and a total of N times (K + 1) highly parallelizable LLM calls are needed for solving an input problem. Assuming that a generated candidate solution is correct with probability p_{gen} > 0 and a comparison between a pair of correct and incorrect solutions identifies the right winner with probability p_{comp} > 0.5 (i.e., better than a random guess), we prove theoretically that the failure probability of the proposed algorithm decays to zero exponentially with respect to N and K: $P(final output is incorrect) le (1 - p_{gen})^N + lceil log_2 N rceil e^{-2 K (p_{comp} - 0.5)^2}.$ Our empirical results with the challenging MMLU-Pro benchmark validate the technical assumptions, as well as the efficacy of the proposed algorithm and the gains from scaling up its test-time compute.

The BITEM team entered both subtasks of the NTCIR-19 R2C2 task with a single agentic pipeline, in which a model searches, reads and records evidence over a movie corpus while an orchestrator holds the record and rules on what may be submitted. A claim is admitted only once an entailment cascade has checked it against the passage it cites, and an answer is released only once enough checked evidence stands behind it. Each question is run three or four times, every pass retrieving from a corpus stripped of what the earlier passes have already seen. The confidence filed with each answer is computed by the orchestrator from what the run leaves behind and is never asked of the model, which is offered no way to rate itself. The two retrieval runs placed 4th and 5th of 22, pooling the passes was worth 0.0709 nDCG@20, and the gain was largest on the multi-hop and post-processing-heavy questions, where the organisers rank the pooled run top of the field. Sixteen of the 25 answer runs were built on passages these two runs supplied, 12 of them filed by other teams. HMR rewards a system whose confidence is high where it answers right and low where it answers wrong. The pipeline reached an accuracy of 0.9219, 6th of 25, while the confidence filed with those answers gave an HMR of 0.4915, 13th. A few rules crafted over those same recorded signals, with no further model call and no further retrieval, raise that to an accuracy of 0.9375, 5th, and an HMR of 0.6985, 9th. Ranking on HMR alone can reward a system for answering wrongly with low confidence, so we propose accHMR, the accuracy multiplied by HMR, which reports the reward in proportion to the accuracy, and on which the revised rules would have scored 0.6549, 5th. For future work, fitting a model on the numbers the pipeline already produces, rather than writing such rules by hand, would be a real step forward.

It is tempting to assume any task solvable by a short program can be taught to a model as its chain-of-thought: write the steps out, fine-tune, and the model follows. This paper shows the assumption fails for an identifiable class of procedures. The testbed is nine reasoning tasks, each from a deterministic generator; public and hidden splits share generators, so held-out data proxies test accuracy. I reverse-engineer the generators into Python solvers, render them as chain-of-thought, and distill into a rank-<= 32 LoRA over a 30B (3.5B-active) Nemotron model. Forward-computable tasks install readily: lookup/arithmetic and an 8-bit boolean task transfer (>= 0.99 and 0.68). Cryptarithm does not: distilling its backtracking search holds at 0.01-0.07 across eleven chain-of-thought designs, RL from verifiable rewards, and self-training, even though a search solver answers 71% of instances. This is not a capability gap. The model does the arithmetic on 97-100% of lines and ranks the correct cipher in its top eight on 71%; it cannot carry the search forward as a left-to-right derivation. Fine-tuning learns the shape of a verifiable elimination step while its verdicts become unconditional templates, correct only 16-57% of the time ("verdict-as-token"). The ceiling holds across backbones from 3B to 671B and across fine-tuning and prompting; a controlled intervention isolates the cause: revealing the cipher key, which turns the derivation forward, lifts the same instances from 0.03 to 0.57. When a procedure's only solution is search over information-free structure, no faithful forward chain-of-thought exists to imitate. The task becomes learnable only by removing the search, precomputing its combinatorial core into a catalog and reducing the trace to recall plus verification; the 1st-place solution reaches Private LB 0.92 this way. What distills is memorization and verification, not search.

What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. This legal determination hinges on a definition of a protected class (ethnicity, gender, religious practice) and an explicit description of the process. When the process is implemented using computers, determining disparate impact (and hence bias) is harder. It might not be possible to disclose the process. In addition, even if the process is open, it might be hard to elucidate in a legal setting how the algorithm makes its decisions. Instead of requiring access to the algorithm, we propose making inferences based on the data the algorithm uses. We make four contributions to this problem. First, we link the legal notion of disparate impact to a measure of classification accuracy that while known, has received relatively little attention. Second, we propose a test for disparate impact based on analyzing the information leakage of the protected class from the other data attributes. Third, we describe methods by which data might be made unbiased. Finally, we present empirical evidence supporting the effectiveness of our test for disparate impact and our approach for both masking bias and preserving relevant information in the data. Interestingly, our approach resembles some actual selection practices that have recently received legal scrutiny.

Self-consistency has emerged as a popular technique for improving large language model accuracy on reasoning tasks. The approach is straightforward: generate multiple reasoning paths and select the most common answer through majority voting. While this reliably boosts accuracy, it remains unclear whether these gains reflect genuine improvements in reasoning quality. We investigate a fundamental question that has not been studied before: does inference scaling improve reasoning faithfulness? We conduct a comprehensive empirical study across four frontier models (GPT-5.2, Claude Opus 4.5, Gemini-3-flash-preview, and DeepSeek-v3.2) on 100 GSM8K mathematical reasoning problems. Our analysis employs bootstrap confidence intervals, McNemar's tests for paired comparisons, and Cohen's d effect sizes to quantify the effects rigorously. The results reveal striking differences across models that challenge common assumptions about self-consistency. GPT-5.2 shows the expected pattern: accuracy improves from 78% to 90% at N=5, with faithfulness remaining relatively stable (0.540 to 0.510). Claude Opus 4.5 tells a completely different story. Its accuracy actually drops from 78% to 74.3% while faithfulness jumps dramatically from 0.270 to 0.891 at N=5. DeepSeek-v3.2, already at 98% accuracy, shows ceiling effects with modest faithfulness gains (0.440 to 0.541). Gemini-3-flash improves from 81% to 86% accuracy with a slight faithfulness decrease (0.260 to 0.212). Problem difficulty analysis reveals that GPT-5.2 solves 82% of hard problems while breaking only 13% of easy ones. Claude, in contrast, breaks 23% of easy problems, explaining its accuracy decrease. These findings matter for practitioners: self-consistency is not universally beneficial, and teams should test their specific models before deployment. We release our code and provide practical recommendations for navigating these tradeoffs.

We introduce ALARB, a dataset and suite of tasks designed to evaluate the reasoning capabilities of large language models (LLMs) within the Arabic legal domain. While existing Arabic benchmarks cover some knowledge-intensive tasks such as retrieval and understanding, substantial datasets focusing specifically on multistep reasoning for Arabic LLMs, especially in open-ended contexts, are lacking. The dataset comprises over 13K commercial court cases from Saudi Arabia, with each case including the facts presented, the reasoning of the court, the verdict, as well as the cited clauses extracted from the regulatory documents. We define a set of challenging tasks leveraging this dataset and reflecting the complexity of real-world legal reasoning, including verdict prediction, completion of reasoning chains in multistep legal arguments, and identification of relevant regulations based on case facts. We benchmark a representative selection of current open and closed Arabic LLMs on these tasks and demonstrate the dataset's utility for instruction tuning. Notably, we show that instruction-tuning a modest 12B parameter model using ALARB significantly enhances its performance in verdict prediction and Arabic verdict generation, reaching a level comparable to that of GPT-4o.

Automated checking pipelines increasingly place one language model as the checker and another (or the same one) as the fixer. We ask whether that wiring changes what the checker reports. Measuring false alarms on human-verified-correct ProcessBench traces with the present task held byte-identical, we find that a completed audit -> repair episode already in the model's context lowers false alarms in 15 of 15 model x wording combinations, by 2.8 to 11.5 percentage points against a length-matched non-audit control, a 9 to 25% reduction relative to that control. The direction contradicts what the accumulated-message literature predicts: an episode whose audit reported an error lowers false alarms further still, at all five wordings on the model where that manipulation lands cleanly, though a negativity asymmetry predicts more flagging. Decomposing the episode finds repair content and audit verdict complementary: different components carry the effect on different model families. Signal-detection analysis locates the change in the threshold rather than in discrimination -- the criterion moves in 15 of 15 combinations and survives correction in 13 while d' survives in none, though the d' test is half as sensitive by construction -- and a hand audit of 50 false alarms finds 82% simply wrong, so at this operating point the shift need not be harmful. With reasoning enabled the effect keeps its relative size on both models tested, and the threshold reading holds there too.

Behaviour-Driven Development (BDD) suites accumulate step-text duplication whose maintenance cost is established in prior work. Existing detection techniques require running the tests (Binamungu et al., 2018-2023) or are confined to a single organisation (Irshad et al., 2020-2022), leaving a gap: a purely static, paraphrase-robust, step-level detector usable on any repository. We fill the gap with cukereuse, an open-source Python CLI combining exact hashing, Levenshtein ratio, and sentence-transformer embeddings in a layered pipeline, released alongside an empirical corpus of 347 public GitHub repositories, 23,667 parsed .feature files, and 1,113,616 Gherkin steps. The step-weighted exact-duplicate rate is 80.2 %; the median-repository rate is 58.6 % (Spearman rho = 0.51 with size). The top hybrid cluster groups 20.7k occurrences across 2.2k files. Against 1,020 pairs manually labelled by the three authors under a released rubric (inter-annotator Fleiss' kappa = 0.84 on a 60-pair overlap), we report precision, recall, and F1 with bootstrap 95 % CIs under two protocols: the primary rubric and a score-free second-pass relabelling. The strongest honest pair-level number is near-exact at F1 = 0.822 on score-free labels; the primary-rubric semantic F1 = 0.906 is inflated by a stratification artefact that pins recall at 1.000. Lexical baselines (SourcererCC-style, NiCad-style) reach primary F1 = 0.761 and 0.799. The paper also presents a CDN-structured critique of Gherkin (Cognitive Dimensions of Notations); eight of fourteen dimensions are rated problematic or unsupported. The tool, corpus, labelled pairs, rubric, and pipeline are released under permissive licences.

AI-based judicial assistance and case prediction have been extensively studied in criminal and civil domains, but remain largely unexplored in consumer law, especially in India. In this paper, we present Nyay-Darpan, a novel two-in-one framework that (i) summarizes consumer case files and (ii) retrieves similar case judgements to aid decision-making in consumer dispute resolution. Our methodology not only addresses the gap in consumer law AI tools but also introduces an innovative approach to evaluate the quality of the summary. The term 'Nyay-Darpan' translates into 'Mirror of Justice', symbolizing the ability of our tool to reflect the core of consumer disputes through precise summarization and intelligent case retrieval. Our system achieves over 75 percent accuracy in similar case prediction and approximately 70 percent accuracy across material summary evaluation metrics, demonstrating its practical effectiveness. We will publicly release the Nyay-Darpan framework and dataset to promote reproducibility and facilitate further research in this underexplored yet impactful domain.

We present a framework for evaluating data-science agents on live, continuously updated data using executable ground truth and format-agnostic factoid scoring. Consider this example query: "what were last week's audience sizes"---the reference answer changes as the underlying data changes, so static references become outdated and standard LLM-as-a-judge pipelines cannot verify responses against a fixed ground truth. Our central contribution, ground-truth-as-code, encodes each expected answer as an executable reference function that recomputes the answer directly from live data at evaluation time, ensuring the reference remains consistent with the system it describes. We combine this with a factoid-level, format-agnostic judge that decomposes both the agent's response and the computed ground truth into atomic claims and scores precision, recall, and accuracy over them, irrespective of the response format (prose, list, table, HTML, etc.). The approach is applicable to agents whose expected outputs can be expressed as executable data computations. We validate the framework through a human--LLM agreement study on an internally developed machine learning skill deployed in production, using a synthetic database constructed to reproduce production schemas and entity relationships. Relative to a natural-language ground-truth baseline, our method achieves a 29% improvement in the Matthews Correlation Coefficient (MCC)---a class-balanced measure of agreement between expert annotators and LLM-as-a-judge predictions---and a 16% reduction in token consumption per test case, while a self-directed baseline lacking explicit ground truth is anti-correlated with human judgment. Agents that perform multi-source data integration and computation over non-stationary data are routinely deployed in industry; we propose ground-truth-as-code as a practical methodology for their evaluation.

Decision models return probabilities over supplied options, but a deployed agent may also need to reply in words. The present study introduces System X, a large language model (LLM) decision model that adds a text-reply option to the LLM-as-Jev readout. When this option wins, or confidence is low, the same model continues from the decision's key-value (KV) cache, avoiding a repeated prompt prefill. Qwen3-0.6B has been fine-tuned with LoRA on Reason-9k and Bitext reply rows. JevBench accuracy shows no statistically significant change (55.4% to 54.5%, p=0.87), while expected calibration error falls from 0.292 to 0.169. Held-out Bitext routing accuracy reaches 98.3%. Cache reuse saves 15-37% of latency on an Apple M4 Pro, with token-identical replies in the FP32 demonstration cases. Scoring options on copies of the prompt cache matches full-sequence scoring to within 1.4e-6 in probability. Adding dialogue, industry and complaint data (System X+) improves support-task results but lowers IFEval accuracy from 55.5% to 45.0%. System X v4 uses Qwen3-1.7B, rebalanced data and teacher-rewritten reply targets. Against its base LLM, JevBench accuracy rises from 55.0% to 61.0% (p=0.04), with no statistically significant IFEval change (p=0.71). A matched latency test on unadapted Qwen3-1.7B saves 17-39%. One LLM judge prefers v4 replies to an unadapted 1.7B second call (31 to 11 pairs, p=0.003); the other's preference is not significant. These reply comparisons also differ in prompts and generation limits. State conflicts and unsupported reply details remain failure modes. Further studies with several seeds, human raters and real support data are recommended.

Probability estimation models play an important role in various fields, such as weather forecasting, recommendation systems, and sports analysis. Among several models estimating probabilities, it is difficult to evaluate which model gives reliable probabilities since the ground-truth probabilities are not available. The win probability estimation model for esports, which calculates the win probability under a certain game state, is also one of the fields being actively studied in probability estimation. However, most of the previous works evaluated their models using accuracy, a metric that only can measure the performance of discrimination. In this work, we firstly investigate the Brier score and the Expected Calibration Error (ECE) as a replacement of accuracy used as a performance evaluation metric for win probability estimation models in esports field. Based on the analysis, we propose a novel metric called Balance score which is a simple yet effective metric in terms of six good properties that probability estimation metric should have. Under the general condition, we also found that the Balance score can be an effective approximation of the true expected calibration error which has been imperfectly approximated by ECE using the binning technique. Extensive evaluations using simulation studies and real game snapshot data demonstrate the promising potential to adopt the proposed metric not only for the win probability estimation model for esports but also for evaluating general probability estimation models.

Combining the answers a large language model (LLM) samples for a question into one decision is a test-time information fusion problem, usually solved by majority voting. Voting is unreliable on difficult questions, where the sampled answers share correlated errors, so the wrong answer can win and drawing more samples makes the decision worse. Selecting a candidate by reading a correctness signal from the model's hidden states is a promising alternative, but its accuracy varies across models and tasks, and no measure indicates when it can be trusted. In this paper, we propose CASE (Correctness-Axis SElection), a dynamic selection combiner that trains a linear gate on the answer-token hidden state and selects the highest-scoring candidate. Its main contribution is decodability, a leakage-free measure of how well the gate ranks a question's correct candidates above its incorrect ones, which predicts whether hidden-state selection will outperform voting. A conventional probe appears accurate only because of question-identity leakage, which vanishes under question-grouped evaluation. On held-out data, decodability predicts the accuracy gain of selection over voting with a Pearson correlation r=0.75 and a decision threshold near AUC=0.60. Across general and medical LLMs, CASE improves over voting by up to 19 points on medium-difficulty questions and 16.8 points on hard questions. Decodability depends on the aligned knowledge a model must recall, not on its scale, and its prediction transfers to an unseen scientific domain within 3.8 points. It thus provides a practical criterion, measurable in advance for a given model and task, for choosing between learned selection and majority voting.

Predicting case outcomes is useful but still an extremely hard task for attorneys and other Law professionals. It is not easy to search case information to extract valuable information as this requires dealing with huge data sets and their complexity. For instance, the complexity of Brazil legal system along with the high litigation rates makes this problem even harder. This paper introduces an approach for predicting Brazilian court decisions which is also able to predict whether the decision will be unanimous. We developed a working prototype which performs 79% of accuracy (F1-score) on a data set composed of 4,043 cases from a Brazilian court. To our knowledge, this is the first study to forecast judge decisions in Brazil.

Automated LLM-as-a-Judge frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, these judges are relied upon to evaluate harmfulness in order to benchmark the robustness of safety against adversarial attacks. However, we show that existing validation protocols fail to account for substantial distribution shifts inherent to red-teaming: diverse victim models exhibit distinct generation styles, attacks distort output patterns, and semantic ambiguity varies significantly across jailbreak scenarios. Through a comprehensive audit using 6642 human-verified labels, we reveal that the unpredictable interaction of these shifts often causes judge performance to degrade to near random chance. This stands in stark contrast to the high human agreement reported in prior work. Crucially, we find that many attacks inflate their success rates by exploiting judge insufficiencies rather than eliciting genuinely harmful content. To enable more reliable evaluation, we propose ReliableBench, a benchmark of behaviors that remain more consistently judgeable, and JudgeStressTest, a dataset designed to expose judge failures. Data available at: https://github.com/SchwinnL/LLMJudgeReliability.

Overconfidence and underconfidence in machine learning classifiers is measured by calibration: the degree to which the probabilities predicted for each class match the accuracy of the classifier on that prediction. How one measures calibration remains a challenge: expected calibration error, the most popular metric, has numerous flaws which we outline, and there is no clear empirical understanding of how its choices affect conclusions in practice, and what recommendations there are to counteract its flaws. In this paper, we perform a comprehensive empirical study of choices in calibration measures including measuring all probabilities rather than just the maximum prediction, thresholding probability values, class conditionality, number of bins, bins that are adaptive to the datapoint density, and the norm used to compare accuracies to confidences. To analyze the sensitivity of calibration measures, we study the impact of optimizing directly for each variant with recalibration techniques. Across MNIST, Fashion MNIST, CIFAR-10/100, and ImageNet, we find that conclusions on the rank ordering of recalibration methods is drastically impacted by the choice of calibration measure. We find that conditioning on the class leads to more effective calibration evaluations, and that using the L2 norm rather than the L1 norm improves both optimization for calibration metrics and the rank correlation measuring metric consistency. Adaptive binning schemes lead to more stablity of metric rank ordering when the number of bins vary, and is also recommended. We open source a library for the use of our calibration measures.

Legal judgment prediction (LJP) aims to function as a judge by making final rulings based on case claims and facts, which plays a vital role in the judicial domain for supporting court decision-making and improving judicial efficiency. However, existing methods often struggle with logical errors when conducting complex legal reasoning. We propose LegalReasoner, which enhances LJP reliability through step-wise verification and correction of the reasoning process. Specifically, it first identifies dispute points to decompose complex cases, and then conducts step-wise reasoning while employing a process verifier to validate each step's logic from correctness, progressiveness, and potential perspectives. When errors are detected, expert-designed attribution and resolution strategies are applied for correction. To fine-tune LegalReasoner, we release the LegalHK dataset, containing 58,130 Hong Kong court cases with detailed annotations of dispute points, step-by-step reasoning chains, and process verification labels. Experiments demonstrate that LegalReasoner significantly improves concordance with court decisions from 72.37 to 80.27 on LLAMA-3.1-70B. The data is available at https://huggingface.co/datasets/weijiezz/LegalHK.

Reinforcement Learning with Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) are the main RL paradigms used in LLM post-training, each offering distinct advantages. However, RLHF struggles with interpretability and reward hacking because it relies on human judgments that usually lack explicit criteria, whereas RLVR is limited in scope by its focus on correctness-based verifiers. We propose Reinforcement Learning with Binary Flexible Feedback (RLBFF), which combines the versatility of human-driven preferences with the precision of rule-based verification, enabling reward models to capture nuanced aspects of response quality beyond mere correctness. RLBFF extracts principles that can be answered in a binary fashion (e.g. accuracy of information: yes, or code readability: no) from natural language feedback. Such principles can then be used to ground Reward Model training as an entailment task (response satisfies or does not satisfy an arbitrary principle). We show that Reward Models trained in this manner can outperform Bradley-Terry models when matched for data and achieve top performance on RM-Bench (86.2%) and JudgeBench (81.4%, #1 on leaderboard as of September 24, 2025). Additionally, users can specify principles of interest at inference time to customize the focus of our reward models, in contrast to Bradley-Terry models. Finally, we present a fully open source recipe (including data) to align Qwen3-32B using RLBFF and our Reward Model, to match or exceed the performance of o3-mini and DeepSeek R1 on general alignment benchmarks of MT-Bench, WildBench, and Arena Hard v2 (at <5% of the inference cost).

Selecting LLM-generated code candidates using LLM-generated tests is challenging because the tests themselves may be incorrect. Existing methods either treat all tests equally or rely on ad-hoc heuristics to filter unreliable tests. Yet determining test correctness requires knowing which codes are correct, creating a circular dependency. Our key insight is that we need not determine test correctness at all: test votes should rank, not merely count. What matters is not how many codes pass a test, but whether the test can distinguish correct from incorrect code. We break the circular dependency via leave-one-out evaluation: hold out one test, rank codes by their aggregate scores on all remaining tests, and measure whether the held-out test's pass/fail pattern agrees with this ranking. We formalize this agreement as the leave-one-out AUC~(LOO-AUC) and prove that the expected LOO-AUC is proportional to each test's ability to separate correct code from incorrect code. Building on this, we propose ACES~(AUC ConsistEncy Scoring) with two complementary variants: ACES-C provides closed-form weights that provably approximate the oracle in expectation under a mild assumption on average test quality; ACES-O drops this assumption and iteratively optimizes a differentiable LOO-AUC objective. Both operate solely on the binary pass matrix with negligible overhead, and achieve state-of-the-art Pass@k on multiple code generation benchmarks.

Recent work on chain-of-thought (CoT) faithfulness reports single aggregate numbers (e.g., DeepSeek-R1 acknowledges hints 39% of the time), implying that faithfulness is an objective, measurable property of a model. This paper demonstrates that it is not. Three classifiers (a regex-only detector, a two-stage regex-plus-LLM pipeline, and an independent Claude Sonnet 4 judge) are applied to 10,276 influenced reasoning traces from 12 open-weight models spanning 9 families and 7B to 1T parameters. On identical data, these classifiers produce overall faithfulness rates of 74.4%, 82.6%, and 69.7%, respectively, with non-overlapping 95% confidence intervals. Per-model gaps range from 2.6 to 30.6 percentage points; all are statistically significant (McNemar's test, p < 0.001). The disagreements are systematic, not random: inter-classifier agreement measured by Cohen's kappa ranges from 0.06 ("slight") for sycophancy hints to 0.42 ("moderate") for grader hints, and the asymmetry is pronounced: for sycophancy, 883 cases are classified as faithful by the pipeline but unfaithful by the Sonnet judge, while only 2 go the other direction. Classifier choice can also reverse model rankings: Qwen3.5-27B ranks 1st under the pipeline but 7th under the Sonnet judge; OLMo-3.1-32B moves in the opposite direction, from 9th to 3rd. The root cause is that different classifiers operationalize related faithfulness constructs at different levels of stringency (lexical mention versus epistemic dependence), and these constructs yield divergent measurements on the same behavior. These results demonstrate that published faithfulness numbers cannot be meaningfully compared across studies that use different classifiers, and that future evaluations should report sensitivity ranges across multiple classification methodologies rather than single point estimates.

A decision model can give probabilities that sum to one for every question yet disagree with itself when the same decision is broken into smaller steps. We study this form of probabilistic coherence in Jev and the English Laya checkpoint, using 2,500 matched examples per system across TREC, CLINC150, and MASSIVE. Across 72,000 classification questions, we compare direct fine-label predictions with broad-category probabilities and predictions reconstructed through those categories. Both systems show substantial disagreement: mean category-level total variation ranges from 0.219 to 0.349 for Jev and from 0.424 to 0.689 for Laya, on a scale where zero means exact agreement. The consequences differ sharply. On CLINC150, reconstruction reduces Jev's accuracy by 22.9 percentage points (paired 95% bootstrap interval: [-24.9, -20.9]) and improves Laya's by 21.3 points ([18.0, 24.5]). The same directions hold across all three datasets, with all six unadjusted accuracy-change intervals excluding zero. Improved accuracy can also accompany less reliable confidence: on MASSIVE, Laya gains 9.2 accuracy points while its expected calibration error rises from 0.046 to 0.124. Error analysis identifies both broad-category mistakes and within-category confusions. These findings show why decision systems need joint evaluation of accuracy, confidence calibration, and probability coherence in the workflow used by an application.

Continuous evaluation of LLM products relies on a strong LLM judge treated as ground truth: a cheap monitor scores every interaction and a team is paged when the score drifts down. But the judge is itself a model behind an API, and a silent version bump or scoring-prompt update changes how it scores -- so every drift alarm is ambiguous between a worse product and a changed judge. We resolve the ambiguity with a fixed, human-labeled anchor set that the current judge re-scores at a steady interleave, a second betting e-process on the judge-versus-human gap, and a guard-window rule returning a verdict in {none, system, judge}. We prove anytime-validity, one-way identification (only the judge can move the anchors), an attribution race whose design law is that the anchors must out-run the main process they guard, and process orthogonality. On two real judge changes, a silent version bump is detected as judge drift in 60/60 runs with zero judge-to-system misattribution, and a contaminating strict-prompt change is correctly attributed on 110 of 120 runs at guard width 300 -- while the industry-default rolling z-test false-alarms on 75% of drift-free streams. Every experiment replicates on a second domain (TL;DR summarization) with nothing re-tuned, and where the domains differ the differences are the ones the race predicts: the strict-prompt change shifts scores harder there, so the anchors fire faster and attribution becomes perfect (240/240). The monitor runs at approximately 0.64 of the cost of strong-judging every item, or 0.21 in a cheaper-but-deafer regime.

When the sources retrieved for a query disagree, the right response depends on why they disagree: a question with several valid answers, a contested topic, stale information and a false source each call for different behaviour. Cattan et al. (2025) showed that telling a generator the conflict type improves its responses by about 24 points, but that predicting the type is hard even for frontier LLMs. We study whether typed decision models, which return probabilities over fixed options in a single forward pass instead of generating text, can do this classification fast and cheaply. Using the CONFLICTS benchmark and the original paper's prompt verbatim, we evaluate all 11 decision models served by one commercial inference gateway, from 7 providers, against Gemini models on identical inputs. Asked directly, the decision models reach 50.0--67.0% accuracy; 10 of the 11 match or exceed Gemini 2.5 Flash, the paper's model (61.3%), at 4--39x lower billed cost (2 were free) and 2.6--6.0x lower latency. The current Gemini 3.8 Flash (70.0%) is significantly more accurate than 8 of them, but sending each decision model's least confident quarter of queries to it gives a cascade statistically tied with it for 8 of the 11, at 25--37% of its cost. End to end, answers generated with the types of 10 of the 11 follow the expected behaviour as often as with the LLM's types. Decomposing the taxonomy into yes/no questions lowers accuracy for every model, and a repair fitted on one model does not transfer. Pre-specified diagnostics show that dates play no measurable role and that sensitivity to source order varies widely between models. Decision models detect a planted false source less reliably than the LLM as hard labels, but their probabilities still separate planted from clean sources. We release code, prompts and all model outputs at https://github.com/Parv17k/decision-models-conflict-typing.