<?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>LLM on Yuchen Du</title><link>https://dudusoar.github.io/tags/llm/</link><description>Recent content in LLM on Yuchen Du</description><generator>Hugo -- 0.164.0</generator><language>en-us</language><lastBuildDate>Mon, 10 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://dudusoar.github.io/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Reviewing the Reviewer: Graph-Enhanced LLMs for E-commerce Appeal Adjudication</title><link>https://dudusoar.github.io/papers/amazon-rj/</link><pubDate>Thu, 26 Feb 2026 20:00:00 -0500</pubDate><guid>https://dudusoar.github.io/papers/amazon-rj/</guid><description>A two-stage LLM agent that uses RAG with graph-based memory to ground fraud-related seller-appeal recommendations in evidence, verification actions, and historical human corrections.</description></item></channel></rss>