<?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 评估 on FisherAI</title>
    <link>https://fisherdaddy.com/tags/llm-%E8%AF%84%E4%BC%B0/</link>
    <description>Recent content in LLM 评估 on FisherAI</description>
    <image>
      <title>FisherAI</title>
      <url>https://fisherdaddy.com/images/papermod-cover.png</url>
      <link>https://fisherdaddy.com/images/papermod-cover.png</link>
    </image>
    <generator>Hugo -- 0.125.7</generator>
    <language>en</language>
    <lastBuildDate>Tue, 27 Oct 2026 00:30:18 +0800</lastBuildDate>
    <atom:link href="https://fisherdaddy.com/tags/llm-%E8%AF%84%E4%BC%B0/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>如何把决策模型用于 Evals（模型评估）</title>
      <link>https://fisherdaddy.com/posts/how-to-use-decision-models-for-evals/</link>
      <pubDate>Tue, 27 Oct 2026 00:30:18 +0800</pubDate>
      <guid>https://fisherdaddy.com/posts/how-to-use-decision-models-for-evals/</guid>
      <description>用 100 条真实 trace 实测 Jev、Perplexity Decider、Liquid d1、Cloudflare Clef 与 OpenAI Decisions：如何调决策阈值、如何权衡 F1 与成本，以及决策模型的概率能否当作置信度使用。</description>
    </item>
  </channel>
</rss>
