<?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>IRT on Cognaptus</title>
    <link>https://cognaptus.com/tags/irt/</link>
    <description>Recent content in IRT on Cognaptus</description>
    <generator>Hugo -- 0.145.0</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 20 Sep 2025 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://cognaptus.com/tags/irt/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Benchmarks That Fight Back: Adaptive Testing for LMs</title>
      <link>https://cognaptus.com/blog/2025-09-20-benchmarks-that-fight-back-adaptive-testing-for-lms/</link>
      <pubDate>Sat, 20 Sep 2025 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2025-09-20-benchmarks-that-fight-back-adaptive-testing-for-lms/</guid>
      <description>Fluid Benchmarking shows why model evaluation should adapt to the model being tested, not merely shrink old benchmarks into cheaper static subsets.</description>
    </item>
  </channel>
</rss>
