arxiv:2601.01739
Wooseok Seo
just1nseo
AI & ML interests
LLM Hallucination & Interpretability
Recent Activity
updated a model about 9 hours ago
just1nseo/qwen3-1.7b-if-rlvr-klabl-kl0p02 published a model about 9 hours ago
just1nseo/qwen3-1.7b-if-rlvr-klabl-kl0p02 updated a model about 9 hours ago
just1nseo/qwen3-1.7b-if-rlvr-klabl-kl0p01Organizations
None yet
models 29
just1nseo/qwen3-1.7b-if-rlvr-klabl-kl0p02
Text Generation • Updated
just1nseo/qwen3-1.7b-if-rlvr-klabl-kl0p01
Text Generation • Updated
just1nseo/qwen3-1.7b-if-rlvr-klabl-kl0p005
Text Generation • Updated
just1nseo/qwen3-1.7b-if-rlvr-klabl-kl0p002
Text Generation • Updated
just1nseo/qwen3-4b-grpo-gptoss120b-t4
Text Generation • Updated
just1nseo/qwen3-4b-grpo-q4b-t5
Text Generation • Updated
just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only
Text Generation • Updated
just1nseo/qwen3-4b-if-rlvr-subset20k-n3-ci95lower-uppermean-flipabstain-ep3
Text Generation • Updated
just1nseo/qwen3-4b-if-rlvr-subset20k-n3-ci95lower-uppermean-strict-ep3
Text Generation • Updated
just1nseo/tulu3-8b-dpo-grpo-q30ba3b-t7
Text Generation • Updated
datasets 7
just1nseo/anchor_cache
Updated • 16
just1nseo/ambifc
Viewer • Updated • 62.8k • 41
just1nseo/anli-train
Viewer • Updated • 56.9k • 20
just1nseo/archetypal_a6k12
Viewer • Updated • 217k • 11
just1nseo/synth-multihop
Viewer • Updated • 25.3k • 20
just1nseo/GrayFacts
Viewer • Updated • 159 • 28
just1nseo/ClearFacts
Viewer • Updated • 1.59k • 47 • 2