Recoverability-Controlled Safety Miscalibration in Large Language Models

본문 미리보기

arXiv:2610.22425v1 Announce Type: new Abstract: Safety-aligned language models are expected to refuse harmful requests while remaining useful for benign ones. However, because many evaluations score only the final response, they often conflate intent understanding with response-level safety behavior. To address this, we introduce RiskCueBench, a recoverability-controlled benchmark that separates these two stages by first measuring whether a model can successfully recover a high-level intent and