Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation 事件

Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation arXiv:2605.13643v2 Announce Type: replace Abstract: On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is available, supervising the full sequence of response tokens should monotonically improve performance. However, we demonstrate that this assumption sometimes fails to hold i