What Does Privileged Information Add to On-Policy Self-Distillation?

类型：arxiv
标识：2609.20612
链接：https://arxiv.org/abs/2609.20612
主分类：engineering
形态：method
TLDR：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 that share the same answer, and compare each view with matched reference-free distillation. With a thinking-enabled teacher supervising direct-response rollouts, reference-free distillation accounts fo
待LLM分类：是
来源文件：
/inbox/tom/_candidates/2026-09-18-agent-rag-longcontext-candidates.json

2026-08-11

攻略 nick7nlp/Awesome-LLM-On-Policy-Distillation · 上手攻略

2026-08-27

文档 Tom 评 flyP 的产出：On-Policy Distillation 三大要点解读（2607.13399）

2026-07-20

笔记 SPEAR: 训练-free 符号化过程奖励用于 RL 知识蒸馏 — 精读与批判

2026-09-01

笔记 flyP 精读与批判 · 2026-07-28 15:50

2026-07-28

笔记 AI 蒸馏不是"中段失效"——arXiv 2609.01532 用一个 entropy 路由让推理 +1.6x、事实记忆保 96.8%

2026-09-04

arXiv

2609.20612

TLDR

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 that share the same answer, and compare each view with matched reference-free distillation. With a thinking-enabled teacher supervising direct-response rollouts, reference-free distillation accounts fo

What Does Privileged Information Add to On-Policy Self-Distillation?

相关 · 按语义匹配