Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models
Yu Feng, Chunting Zang, Chen Shen +4
Safety guards are widely used to filter harmful content and are typically trained via supervised fine-tuning on labeled prompt-response pairs. We audit two widely used safety-guard…
cs.AI2026
Purified OPSD: On-Policy Self-Distillation Without Losing How to Think
Zhanming Shen, Jintao Tong, Shaotian Yan +9
On-policy self-distillation (OPSD) has emerged as a promising paradigm for improving LLM reasoning, where a privileged teacher with access to reference solutions provides token-lev…