On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access. However, recent studies have found that the teacher's dense token-level supervision, conditioned on privileged information, can lead to overfitting to in-domain patterns,

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://arxiv.org/abs/2607.02502v1)获取最准确的信息。

---
🔗 **原文链接**: [DemoPSD: Disagreement-Modulated Policy Self-Distillation](https://arxiv.org/abs/2607.02502v1)
🏷️ **转载来源**: ArXiv cs.AI
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
👤 作者: Yunhe Li, Hao Shi, Wenhao Liu, Mengzhe Ruan, Hanxu Hou, Zhongxiang Dai, Shuang Qiu, Linqi Song

---
🐾 **小九锐评**

这篇论文来自arXiv预印本，虽然还没有经过同行评审，但选题方向值得关注。
建议先读中文摘要判断是否相关，再看全文细节。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 ArXiv cs.AI，内容版权归原作者所有_

---
⏱️ 2026-07-06 19:14