Recovering Reliable Supervision via Critique-Guided On-Policy Distillation
On-policy distillation (OPD) trains a student model on its own rollouts with token-level supervision from a teacher, assuming that the teacher can reach a correct answer from any prefix the student writes. We call this property the recoverability of the teacher and show it fails on incorrect rollouts: the teacher follows student errors, although it recognizes them. We propose CriticOPD, using…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
