arxiv:2610.19525
Wooseok Seo
just1nseo
AI & ML interests
LLM Hallucination & Interpretability
Recent Activity
updated a model about 1 hour ago
just1nseo/qwen3-1.7b-think-if-rlvr-constraint-only-kl0p02 published a model about 1 hour ago
just1nseo/qwen3-1.7b-think-if-rlvr-constraint-only-kl0p02 updated a model about 18 hours ago
just1nseo/tulu3-8b-dpo-grpo-tulu3rm-ifbench-eq2-a7Organizations
None yet
models 40
just1nseo/qwen3-1.7b-think-if-rlvr-constraint-only-kl0p02
Text Generation • Updated
just1nseo/tulu3-8b-dpo-grpo-tulu3rm-ifbench-eq2-a7
Text Generation • Updated
just1nseo/qwen3-4b-if-rlvr-constraint-only-kl0p05
Text Generation • Updated • 1
just1nseo/qwen3-4b-if-rlvr-constraint-only-kl0p02
Text Generation • Updated • 1
just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05
Text Generation • Updated
just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p02
Text Generation • Updated
just1nseo/qwen3-1.7b-if-rlvr-anchor-pyx0001
Text Generation • Updated
just1nseo/qwen3-1.7b-if-rlvr-anchor-pyx0005
Text Generation • Updated
just1nseo/qwen3-4b-ifrlvr-grpo-judge-30ba3b
Text Generation • Updated
just1nseo/tulu3-8b-dpo-grpo-intentcheck-q30ba3b
Text Generation • Updated
datasets 7
just1nseo/anchor_cache
Updated • 6
just1nseo/ambifc
Viewer • Updated • 62.8k • 50
just1nseo/anli-train
Viewer • Updated • 56.9k • 13
just1nseo/archetypal_a6k12
Viewer • Updated • 217k • 28
just1nseo/synth-multihop
Viewer • Updated • 25.3k • 29
just1nseo/GrayFacts
Viewer • Updated • 159 • 59
just1nseo/ClearFacts
Viewer • Updated • 1.59k • 54 • 2