<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>微调 on MessageDaily</title><link>https://inkeast.github.io/MessageDaily/tags/%E5%BE%AE%E8%B0%83/</link><description>Recent content in 微调 on MessageDaily</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Mon, 13 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://inkeast.github.io/MessageDaily/tags/%E5%BE%AE%E8%B0%83/index.xml" rel="self" type="application/rss+xml"/><item><title>Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models 精读</title><link>https://inkeast.github.io/MessageDaily/posts/2026-07-13-incomplete-learning-sft-paper-reading/</link><pubDate>Mon, 13 Jul 2026 00:00:00 +0000</pubDate><guid>https://inkeast.github.io/MessageDaily/posts/2026-07-13-incomplete-learning-sft-paper-reading/</guid><description>这篇 ACL 2026 Main 论文首次系统性地揭示了「不完全学习现象」（ILP）：即使训练损失收敛，LLM 仍有约15%的训练样本无法被正确复现。论文将这一现象归因为五个可诊断的来源，并提出了一个「先诊断、再对症下药」的框架，证明了SFT失败的异质性——不同原因需要不同解法。</description></item></channel></rss>