Paper recorded by Signals 4 on 2026-11-03 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-11-03 on arXiv · recorded by Signals 4 on 2026-11-04
Category: cs.CL · 自然语言处理 · first seen 2026-11-04
Knowledge distillation improves a student model's reasoning ability through supervision from a teacher. On-policy self-distillation (OPSD) uses the same model as both teacher and student under different contexts: the student generates reasoning trajectories from the question alone, while the teacher additionally receives a complete worked example and provides token-level supervision along those tr