arxiv:2510.00492
Sangwoo Park
Sangsang
AI & ML interests
I do LLM Safety & Reasoning research (KAIST AI)
Recent Activity
updated
a dataset
10 days ago
Sangsang/thinksafe_r1-distill_1.5B_force_2_harmful-refusal
published
a dataset
10 days ago
Sangsang/thinksafe_r1-distill_1.5B_force_2_harmful-refusal
updated
a dataset
10 days ago
Sangsang/thinksafe_r1-distill_1.5B_force_1_harmful-refusal
Organizations
None yet
models
23
Sangsang/R1-1.5B-thinksafe-r1-1.5B-n5-refusal-math-20k-5-pm
Text Generation
•
Updated
•
36
Sangsang/R1-1.5B-thinksafe-r1-1.5B-n5-refusal-math-20k-5
Text Generation
•
Updated
•
40
Sangsang/qwen3-0.6B-thinksafe-qwen-0.6B-n5-refusal-math-20k-5-pm
Text Generation
•
Updated
•
37
Sangsang/qwen3-0.6B-thinksafe-qwen-0.6B-n5-refusal-math-20k-5
Text Generation
•
Updated
•
38
Sangsang/safepath_Qwen3-8B
Text Generation
•
Updated
•
62
Sangsang/safepath_Qwen3-4B
Text Generation
•
Updated
•
72
Sangsang/safepath_Qwen3-1.7B
Text Generation
•
Updated
•
74
Sangsang/safepath_Qwen3-0.6B
Text Generation
•
Updated
•
100
Sangsang/0923_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL
Updated
Sangsang/Qwen2.5-7B-Instruct-malware
Updated
datasets
35
Sangsang/thinksafe_r1-distill_1.5B_force_2_harmful-refusal
Viewer
•
Updated
•
34.9k
•
22
Sangsang/thinksafe_r1-distill_1.5B_force_1_harmful-refusal
Viewer
•
Updated
•
34.7k
•
22
Sangsang/thinksafe_r1-distill_1.5B_force_2_harmful
Viewer
•
Updated
•
38.6k
•
19
Sangsang/thinksafe_r1-distill_1.5B_force_1_harmful
Viewer
•
Updated
•
38.6k
•
20
Sangsang/thinksafe_r1-distill_1.5B_forcing_3_debug
Viewer
•
Updated
•
62
•
17
Sangsang/thinksafe_r1-distill_1.5B_forcing_2_debug
Viewer
•
Updated
•
62
•
38
Sangsang/ThinkSafe-4B-n5-refusal_20000_5
Viewer
•
Updated
•
235k
•
19
Sangsang/ThinkSafe-0.6B-n5-refusal_20000_5
Viewer
•
Updated
•
204k
•
25
Sangsang/ThinkSafe-R1-Distill-7B-n5-refusal_20000_5
Viewer
•
Updated
•
261k
•
26
Sangsang/ThinkSafe-R1-Distill-1.5B-n5-refusal_20000_5
Viewer
•
Updated
•
204k
•
25