AI RESEARCH
Beyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label Enhancement
arXiv CS.CL
•
ArXi:2605.07883v1 Announce Type: new Large Language Models (LLMs) rely on safety alignment to obey safe requests while refusing harmful ones. However, traditional refusal mechanisms often lead to "rigid rejection," where a general template (e.g., "I cannot fulfill this request") indiscriminately triggers refusals and severely undermines the naturalness of interactions between humans and LLMs. To address this issue, LANCE is proposed in this paper to ensure safe yet flexible and natural responses via label enhancement.