Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning Models
Experiments on three LRMs show that SaLT-DPO consistently reduces unsafe rates for both reasoning and answer segments while mitigating degradation in benign compliance and preserving general reasoning performance.
Jungmin Yun, Junehyoung Kwon, Hayeong Ryu et al.
· 0 citations