<?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 Undertide</title><link>https://www.kircerta.com/tags/llm/</link><description>Recent content in LLM on Undertide</description><generator>Hugo -- 0.161.1</generator><language>en-us</language><lastBuildDate>Mon, 23 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.kircerta.com/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Do LLMs Actually Follow Instructions? A Factorial Experiment</title><link>https://www.kircerta.com/posts/academica/essays/305_factorial_llm/</link><pubDate>Mon, 23 Mar 2026 00:00:00 +0000</pubDate><guid>https://www.kircerta.com/posts/academica/essays/305_factorial_llm/</guid><description>A 2³ factorial experiment measuring how prompt strategy, contextual examples, and model reasoning capability affect LLM instruction-following compliance.</description></item></channel></rss>