Inductive Feedback for Mixed-Policy Distillation
Verbal feedback can identify errors and prescribe corrections, providing rich supervision for language-model post-training even when reliable programmatic verifiers are unavailable. Such feedback, often generated by a capable model, can be used to condition the teacher in on-policy distillation, which trains the studen...
Amir Moeini, Huai-Jiang Zhu, Daniel Havir et al.
· 0 citations