<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Knowledge Editiing | Haowei Liu</title><link>https://jamesl404.github.io/tags/knowledge-editiing/</link><atom:link href="https://jamesl404.github.io/tags/knowledge-editiing/index.xml" rel="self" type="application/rss+xml"/><description>Knowledge Editiing</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Tue, 10 Dec 2024 00:00:00 +0000</lastBuildDate><image><url>https://jamesl404.github.io/media/icon_hu7729264130191091259.png</url><title>Knowledge Editiing</title><link>https://jamesl404.github.io/tags/knowledge-editiing/</link></image><item><title>Knowledge Editing</title><link>https://jamesl404.github.io/project/knowledge_edting/</link><pubDate>Tue, 10 Dec 2024 00:00:00 +0000</pubDate><guid>https://jamesl404.github.io/project/knowledge_edting/</guid><description>&lt;p>Focuses on efficiently modifying LLMs to update or correct specific facts while preserving overall model performance. By leveraging targeted fine-tuning, memory-efficient methods, or intervention-based techniques, the project aims to enable real-time updates without requiring full retraining.&lt;/p></description></item></channel></rss>