HF Daily Papers
· Papers
ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation
On-policy distillation (OPD) improves LLM reasoning by training a student model on its own generated outputs, but standard OPD treats all student-generated outputs (SGOs) equally regardless of their informativeness. We observe a consistent asymmetry in controlled filtering experiments: in both OPD a