
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>HANS</title>
      <link>https://www.hansking.cn/blog</link>
      <description>A posts created with Next.js and Tailwind.css</description>
      <language>en-us</language>
      <managingEditor>admin@hansking.cn (HANS)</managingEditor>
      <webMaster>admin@hansking.cn (HANS)</webMaster>
      <lastBuildDate>Mon, 09 Feb 2026 10:00:00 GMT</lastBuildDate>
      <atom:link href="https://www.hansking.cn/tags/数据集/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://www.hansking.cn/blog/2026gou-jian-huang-jin-shu-ju-ji-rang-ping-ce-cong-gan-jue-bian-cheng-zheng-ju</guid>
    <title>构建黄金数据集：让评测从感觉变成证据</title>
    <link>https://www.hansking.cn/blog/2026gou-jian-huang-jin-shu-ju-ji-rang-ping-ce-cong-gan-jue-bian-cheng-zheng-ju</link>
    <description>[{&quot;value&quot;:&quot;构建黄金数据集：让评测从感觉变成证据&quot;,&quot;url&quot;:&quot;#构建黄金数据集让评测从感觉变成证据&quot;,&quot;depth&quot;:1},{&quot;value&quot;:&quot;一、先定义数据集要回答什么问题&quot;,&quot;url&quot;:&quot;#一先定义数据集要回答什么问题&quot;,&quot;depth&quot;:2},{&quot;value&quot;:&quot;二、样本要覆盖真实分布和危险边界&quot;,&quot;url&quot;:&quot;#二样本要覆盖真实分布和危险边界&quot;,&quot;depth&quot;:2},{&quot;value&quot;:&quot;三、期望答案要写成可判断的标准&quot;,&quot;url&quot;:&quot;#三期望答案要写成可判断的标准&quot;,&quot;depth&quot;:2},{&quot;value&quot;:&quot;四、标注需要规则，也需要人&quot;,&quot;url&quot;:&quot;#四标注需要规则也需要人&quot;,&quot;depth&quot;:2},{&quot;value&quot;:&quot;五、时间切分和客户切分防止污染&quot;,&quot;url&quot;:&quot;#五时间切分和客户切分防止污染&quot;,&quot;depth&quot;:2},{&quot;value&quot;:&quot;六、版本化和变更记录不能省&quot;,&quot;url&quot;:&quot;#六版本化和变更记录不能省&quot;,&quot;depth&quot;:2},{&quot;value&quot;:&quot;七、指标要和数据集结构对应&quot;,&quot;url&quot;:&quot;#七指标要和数据集结构对应&quot;,&quot;depth&quot;:2},{&quot;value&quot;:&quot;八、黄金集要服务模型、RAG 和 Agent&quot;,&quot;url&quot;:&quot;#八黄金集要服务模型rag-和-agent&quot;,&quot;depth&quot;:2},{&quot;value&quot;:&quot;九、数据集不是建完就结束&quot;,&quot;url&quot;:&quot;#九数据集不是建完就结束&quot;,&quot;depth&quot;:2},{&quot;value&quot;:&quot;总结：黄金数据集是一种工程记忆&quot;,&quot;url&quot;:&quot;#总结黄金数据集是一种工程记忆&quot;,&quot;depth&quot;:2}]</description>
    <pubDate>Mon, 09 Feb 2026 10:00:00 GMT</pubDate>
    <author>admin@hansking.cn (HANS)</author>
    <category>AI</category><category>LLM</category><category>数据集</category><category>评测</category><category>工程实践</category>
  </item>

    </channel>
  </rss>
