Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight 事件

Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight arXiv:2606.00424v1 Announce Type: new Abstract: As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, limiting both weak-to-strong generalization and scalable oversight. We study a more tractable form of weak supervision: using a weak model as a critic rather than as a labeler or judge. Instead of solving the tas