AI RESEARCH
When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
arXiv CS.AI
•
ArXi:2605.21606v1 Announce Type: cross On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher, but its standard objective weights all generated tokens equally, implicitly treating the privileged teacher target as equally reliable at every student-visited prefix. Existing entropy-based OPD methods relax this uniformity by modulating token-level supervision with teacher entropy, but high teacher entropy in reasoning has an ambiguous reliability meaning: it can reflect either non-viable uncertainty or benign solution diversity.