<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM Evaluation | Muhammed Yusuf Kocyigit</title><link>https://yusufkocyigit.me/tag/llm-evaluation/</link><atom:link href="https://yusufkocyigit.me/tag/llm-evaluation/index.xml" rel="self" type="application/rss+xml"/><description>LLM Evaluation</description><generator>Wowchemy (https://wowchemy.com)</generator><language>en-us</language><copyright>© 2026 Muhammed Yusuf Kocyigit</copyright><lastBuildDate>Sun, 13 Jul 2025 00:00:00 +0000</lastBuildDate><image><url>https://yusufkocyigit.me/media/icon_hu0b7a4cb9992c9ac0e91bd28ffd38dd00_9727_512x512_fill_lanczos_center_3.png</url><title>LLM Evaluation</title><link>https://yusufkocyigit.me/tag/llm-evaluation/</link></image><item><title>Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation</title><link>https://yusufkocyigit.me/publication/overestimation/</link><pubDate>Sun, 13 Jul 2025 00:00:00 +0000</pubDate><guid>https://yusufkocyigit.me/publication/overestimation/</guid><description/></item><item><title>Evaluation Data Contamination in LLMs: How Do We Measure It and (When) Does It Matter?</title><link>https://yusufkocyigit.me/publication/contamination/</link><pubDate>Wed, 06 Nov 2024 00:00:00 +0000</pubDate><guid>https://yusufkocyigit.me/publication/contamination/</guid><description/></item><item><title>Western, Religious or Spiritual: An Evaluation of Moral Justification in Large Language Models</title><link>https://yusufkocyigit.me/publication/wsa/</link><pubDate>Mon, 13 Nov 2023 00:00:00 +0000</pubDate><guid>https://yusufkocyigit.me/publication/wsa/</guid><description/></item></channel></rss>