作者位次 #2/5ACL 2026Findings· Findings of ACL
You Only Need One Single Token to Refine Safety Alignment
Wenqian Yu · Shuo Chen · Zhijiang Li · Zhipeng Wang · Jindong Gu
摘要
Large language models (LLMs) face a critical alignment challenge: balancing safety with helpfulness. Excessive safety can lead to over-refusal, where models reject harmful-looking yet benign queries, severely limiting utility.Existing training-free interventions offer an efficient way to mitigate...