arxiv:2601.23143
Sangwoo Park
Sangsang
AI & ML interests
I do LLM Safety & Reasoning research (KAIST AI)
Recent Activity
updated
a model 1 day ago
Sangsang/ci_feedback_both_feedback_jsd_b0p8_ema0p999 updated
a model 1 day ago
Sangsang/ci_feedback_both_feedback_jsd_b0p8 published
a model 1 day ago
Sangsang/ci_feedback_both_feedback_jsd_b0p8_ema0p999 Organizations
None yet
models 163
Sangsang/ci_feedback_both_feedback_jsd_b0p8_ema0p999
Text Generation • 8B • Updated
• 405
Sangsang/ci_feedback_both_feedback_jsd_b0p8
Text Generation • 8B • Updated
• 395
Sangsang/ContextRLDEMO-Qwen3-4B-Instruct-2048-ep3
Text Generation • 4B • Updated
• 439
Sangsang/ContextRLDEMO-Qwen3-4B-Instruct-4096-ep3
Text Generation • 4B • Updated
• 22
Sangsang/CI-7B-CI-RL-merged
Text Generation • 8B • Updated
• 53
Sangsang/CI-7B-Feedback-merged
Text Generation • 8B • Updated
• 49
Sangsang/CI-7B-SFT-merged
Text Generation • 8B • Updated
• 38
Sangsang/Qwen2.5-7B-Instruct-ci-rl
Text Generation • Updated
• 17
Sangsang/Qwen2.5-7B-Instruct-feedback
Text Generation • Updated
• 14
Sangsang/Llama-3.1-8B-Instruct_CI-RL-ep30
Text Generation • Updated
• 7
datasets 75
Sangsang/CI-Qwen2.5-7B-Instruct-Augmented-Responses
Viewer
• Updated
• 729 • 22
Sangsang/CI-Qwen2.5-32B-Instruct-Augmented-Responses
Viewer
• Updated
• 729 • 44
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-7B-Instruct_merged
Viewer
• Updated
• 729 • 42
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-32B-Instruct_merged
Viewer
• Updated
• 729 • 25
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-7B-Instruct_allowed
Viewer
• Updated
• 729 • 10
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-32B-Instruct_allowed
Viewer
• Updated
• 729 • 9
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-32B-Instruct
Viewer
• Updated
• 729 • 46
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-7B-Instruct
Viewer
• Updated
• 729 • 20
Sangsang/CT-Dataset
Viewer
• Updated
• 29.1k • 37
Sangsang/CT-sft-training-dataset
Viewer
• Updated
• 83.1k • 5