Hyounghun Kim

Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models

This paper decomposes a response in the safety-tuning dataset into two distinct components: a boilerplate refusal statement and a rationale explaining the refusal, and shows that refusal statements impede accurate discrimination between harmful and benign queries by inducing reliance on superficial cues.