arxiv:2601.23143
Sangwoo Park
Sangsang
AI & ML interests
I do LLM Safety & Reasoning research (KAIST AI)
Recent Activity
updated a dataset about 8 hours ago
Sangsang/CI_v2_DeepSeek-R1-Distill-Llama-8B_disallowed published a dataset about 8 hours ago
Sangsang/CI_v2_DeepSeek-R1-Distill-Llama-8B_disallowed updated a dataset about 8 hours ago
Sangsang/CI_v2_DeepSeek-R1-Distill-Qwen-7B_disallowedOrganizations
None yet
models 171
Sangsang/ci-feedback_weighted_asym_bi_kl_fixed_ema_Qwen2.5-7B-Instruct_bw1p6_fw0p4_ema0p999_ep30
Text Generation • 8B • Updated • 24
Sangsang/ci-feedback_weighted_asym_bi_kl_fixed_ema_Qwen2.5-7B-Instruct_bw1p0_fw1p0_ema0p999_ep30
Text Generation • 8B • Updated • 32
Sangsang/ci-feedback_both_ema_plus_interp_Qwen2.5-7B-Instruct_jsd_b0p8_ema0p999_stw0p3_ep30
Text Generation • 8B • Updated • 25
Sangsang/ci-feedback_both_interp_Qwen2.5-7B-Instruct_from_Qwen2.5-7B-Instruct_jsd_b0p8_stw0p3_ep30
Text Generation • 8B • Updated • 33
Sangsang/ci-feedback_both_ema_Qwen2.5-7B-Instruct_jsd_b0p8_ema0p999_ep30
Text Generation • 8B • Updated • 37
Sangsang/ci-feedback_both_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30
Text Generation • 8B • Updated • 44
Sangsang/ci-feedback_disallowed_ema_Qwen2.5-7B-Instruct_jsd_b0p8_ema0p999_ep30
Text Generation • 8B • Updated • 31
Sangsang/ci-feedback_disallowed_ema_Qwen2.5-7B-Instruct_reverse_kl_ema0p999_ep30
Text Generation • 8B • Updated • 39
Sangsang/ci_feedback_both_feedback_jsd_b0p8_ema0p999
Text Generation • 8B • Updated • 428
Sangsang/ci_feedback_both_feedback_jsd_b0p8
Text Generation • 8B • Updated • 421
datasets 82
Sangsang/CI_v2_DeepSeek-R1-Distill-Qwen-7B_disallowed
Viewer • Updated • 729
Sangsang/CI_v2_DeepSeek-R1-Distill-Llama-8B_disallowed
Viewer • Updated • 729
Sangsang/CI_v2_Qwen3-4B-Instruct-2507_disallowed
Viewer • Updated • 729
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B-Instruct-2507_all
Viewer • Updated • 729 • 9
Sangsang/ContextualIntegritySyntheticDataset_DeepSeek-R1-Distill-Qwen-7B_all
Viewer • Updated • 729 • 10
Sangsang/ContextualIntegritySyntheticDataset_DeepSeek-R1-Distill-Llama-8B_all
Viewer • Updated • 729 • 8
Sangsang/ContextualIntegritySyntheticDataset_DeepSeek-R1-Distill-Llama-8B_disallowed
Viewer • Updated • 729 • 3
Sangsang/CI-Qwen2.5-7B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 25
Sangsang/CI-Qwen2.5-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 47
Sangsang/ContextualIntegritySyntheticDataset_Qwen2.5-7B-Instruct_merged
Viewer • Updated • 729 • 86