Paper recorded by Signals 4 on 2026-09-17 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-17 on arXiv · recorded by Signals 4 on 2026-09-18
Category: cs.CL · 自然语言处理 · first seen 2026-09-18
On-policy self-distillation (OPSD) lets a language model learn from a frozen copy of itself that sees an answer or a worked solution. Giving the teacher this extra information seems to offer the student more to learn, but how much does it add beyond distillation itself? To isolate that contribution, we construct AMPLE-Math, a reusable suite of 5,319 mathematical problems with six reasoning views t