Rethinking On-Policy Distillation of Large Language Models II: One Training Example
On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. Existing work has mainly studied its algorithmic behavior, leaving the role of training data unclear. We examine this role at the data-minimal limit by training on a single query. One-shot OPD keeps impro...
Zi-Xuan Fu, Bing-Xiang He, Yu-Xin Zuo et al.
· 24 citations
· ⚡1