Recovering Reliable Supervision via Critique-Guided On-Policy Distillation
🔗 https://huggingface.co/papers/2610.20572 ↗CriticOPD improves on-policy distillation by using teacher critiques to restore recoverability, enabling students to revise incorrect reasoning and achieve stronger mathematical reasoning performance.
內容為收集當日抓取的摘要原文。