AI RESEARCH
THINKSAFE: Self-Generated Safety Alignment for Reasoning Models
arXiv CS.AI
•
ArXi:2601.23143v2 Announce Type: replace Large reasoning models (LRMs) achieve remarkable performance by leveraging reinforcement learning (RL) on reasoning tasks to generate long chain-of-thought (CoT) reasoning. However, this over-optimization often prioritizes compliance, making models vulnerable to harmful prompts. To mitigate this safety degradation, recent approaches rely on external teacher distillation, yet this