arxiv:2601.23143
Sangwoo Park
Sangsang
AI & ML interests
I do LLM Safety & Reasoning research (KAIST AI)
Recent Activity
updated
a dataset about 1 hour ago
Sangsang/CI-Qwen2.5-7B-Instruct-Augmented-Responses published
a dataset about 1 hour ago
Sangsang/CI-Qwen2.5-7B-Instruct-Augmented-Responses updated
a dataset about 4 hours ago
Sangsang/CI-Qwen2.5-32B-Instruct-Augmented-Responses Organizations
None yet
models 154
Sangsang/Llama-3.1-8B-Instruct_CI-RL-ep30
Text Generation • Updated
• 7
Sangsang/Qwen2.5-14B-Instruct_pm_think_ep5
15B • Updated
• 10
Sangsang/DeepSeek-R1-Distill-Qwen-14B_pm_ep5
15B • Updated
• 10
Sangsang/Qwen2.5-7B-Instruct_pm_think_ep5
8B • Updated
• 144
Sangsang/DeepSeek-R1-Distill-Qwen-7B_pm_ep5
8B • Updated
• 37
Sangsang/thinksafe-r1-1.5B-ablation_R32_BZ64_Gen8
Text Generation • Updated
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-e3
Text Generation • Updated
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-e2
Text Generation • Updated
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-16-pm-e3
Text Generation • Updated
Sangsang/R1-8B-thinksafe-r1-8B-ablation-32-pm-e3
Text Generation • Updated
datasets 75
Sangsang/CI-Qwen2.5-7B-Instruct-Augmented-Responses
Updated
Sangsang/CI-Qwen2.5-32B-Instruct-Augmented-Responses
Updated
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-7B-Instruct_merged
Viewer
• Updated
• 729
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-32B-Instruct_merged
Viewer
• Updated
• 729
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-7B-Instruct_allowed
Viewer
• Updated
• 729
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-32B-Instruct_allowed
Viewer
• Updated
• 729
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-32B-Instruct
Viewer
• Updated
• 729 • 23
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-7B-Instruct
Viewer
• Updated
• 729 • 3
Sangsang/CT-Dataset
Viewer
• Updated
• 29.1k • 109
Sangsang/CT-sft-training-dataset
Viewer
• Updated
• 83.1k • 19