作者位次 #3/6ACL 2026Findings· Findings of ACL
Health- ORSC -Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context
Zhihao Zhang · Liting Huang · Guanghao Wu · Preslav Nakov · Heng Ji · Usman Naseem
摘要
Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in over-refusal of benign queries or unsafe compliance with harmful ones. While existing benchmarks measure these extremes, they fail to evaluate Safe Completion: the...