arxiv:2601.01739
Wooseok Seo
just1nseo
AI & ML interests
LLM Hallucination & Interpretability
Recent Activity
updated a model about 6 hours ago
just1nseo/qwen3-4b-if-rlvr-subset4k-ep3 published a model about 16 hours ago
just1nseo/qwen3-4b-if-rlvr-subset4k-ep3 updated a model about 19 hours ago
just1nseo/llama31-tulu3-8b-dpo-if-rlvr-judge-onlyOrganizations
None yet
models 15
just1nseo/qwen3-4b-if-rlvr-subset4k-ep3
Text Generation • Updated
just1nseo/llama31-tulu3-8b-dpo-if-rlvr-judge-only
Text Generation • Updated
just1nseo/llama31-tulu3-8b-dpo-if-rlvr-anchor-judge
Text Generation • Updated
just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only
Text Generation • Updated
just1nseo/llama31-8b-if-rlvr-anchor-pyx01
Text Generation • Updated
just1nseo/llama31-8b-if-rlvr-constraint-only
Text Generation • Updated
just1nseo/olmo3-7b-think-if-rlvr-anchor-pyx01-pp0-8k
Text Generation • Updated
just1nseo/olmo3-7b-think-if-rlvr-constraint-only-pp0-8k
Text Generation • Updated
just1nseo/qwen3-8b-v26-3-render-aug-20260505-keep-systematic-final
Text Generation • 8B • Updated • 6
just1nseo/qwen3-8b-v26-3-render-aug-20260505-keep-systematic-step800
Text Generation • 8B • Updated • 9
datasets 7
just1nseo/anchor_cache
Updated • 35
just1nseo/ambifc
Viewer • Updated • 62.8k • 35
just1nseo/anli-train
Viewer • Updated • 56.9k • 30
just1nseo/archetypal_a6k12
Viewer • Updated • 217k • 34
just1nseo/synth-multihop
Viewer • Updated • 25.3k • 29
just1nseo/GrayFacts
Viewer • Updated • 159 • 32
just1nseo/ClearFacts
Viewer • Updated • 1.59k • 43 • 2