GR-OPD: Group-Relative Sequence Credit for On-Policy Distillation
On-policy distillation (OPD) provides token-level teacher feedback, yet common sampled-token updates assign credit locally and omit the effects of earlier actions on subsequent feedback. We introduce \method{} (Group-Relative On-Policy Distillation), which decouples feedback computation from credit assignment by aggreg...
Yu-Shu Wang, Ren-Kai Yang, Jing-Cao Xu et al.
· 0 citations