<?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>Min-P on Answer</title>
    <link>https://answer.freetools.me/tags/min-p/</link>
    <description>Recent content in Min-P on Answer</description>
    <generator>Hugo -- 0.152.2</generator>
    <language>zh-cn</language>
    <lastBuildDate>Thu, 12 Mar 2026 06:53:41 +0800</lastBuildDate>
    <atom:link href="https://answer.freetools.me/tags/min-p/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>大模型如何选择下一个词：从概率预测到文本生成的完整技术链路</title>
      <link>https://answer.freetools.me/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%A6%82%E4%BD%95%E9%80%89%E6%8B%A9%E4%B8%8B%E4%B8%80%E4%B8%AA%E8%AF%8D%E4%BB%8E%E6%A6%82%E7%8E%87%E9%A2%84%E6%B5%8B%E5%88%B0%E6%96%87%E6%9C%AC%E7%94%9F%E6%88%90%E7%9A%84%E5%AE%8C%E6%95%B4%E6%8A%80%E6%9C%AF%E9%93%BE%E8%B7%AF/</link>
      <pubDate>Thu, 12 Mar 2026 06:53:41 +0800</pubDate>
      <guid>https://answer.freetools.me/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%A6%82%E4%BD%95%E9%80%89%E6%8B%A9%E4%B8%8B%E4%B8%80%E4%B8%AA%E8%AF%8D%E4%BB%8E%E6%A6%82%E7%8E%87%E9%A2%84%E6%B5%8B%E5%88%B0%E6%96%87%E6%9C%AC%E7%94%9F%E6%88%90%E7%9A%84%E5%AE%8C%E6%95%B4%E6%8A%80%E6%9C%AF%E9%93%BE%E8%B7%AF/</guid>
      <description>深入解析大语言模型文本生成的核心技术原理，从Logits的本质、Softmax转换、到各种解码策略的博弈，再到神经文本退化问题与参数协同的最佳实践，为你揭示&amp;#34;模型做决策&amp;#34;背后的完整技术真相。</description>
    </item>
    <item>
      <title>大模型解码策略全景解析：从贪婪搜索到动态阈值采样的二十年演进</title>
      <link>https://answer.freetools.me/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%A7%A3%E7%A0%81%E7%AD%96%E7%95%A5%E5%85%A8%E6%99%AF%E8%A7%A3%E6%9E%90%E4%BB%8E%E8%B4%AA%E5%A9%AA%E6%90%9C%E7%B4%A2%E5%88%B0%E5%8A%A8%E6%80%81%E9%98%88%E5%80%BC%E9%87%87%E6%A0%B7%E7%9A%84%E4%BA%8C%E5%8D%81%E5%B9%B4%E6%BC%94%E8%BF%9B/</link>
      <pubDate>Wed, 11 Mar 2026 23:31:16 +0800</pubDate>
      <guid>https://answer.freetools.me/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%A7%A3%E7%A0%81%E7%AD%96%E7%95%A5%E5%85%A8%E6%99%AF%E8%A7%A3%E6%9E%90%E4%BB%8E%E8%B4%AA%E5%A9%AA%E6%90%9C%E7%B4%A2%E5%88%B0%E5%8A%A8%E6%80%81%E9%98%88%E5%80%BC%E9%87%87%E6%A0%B7%E7%9A%84%E4%BA%8C%E5%8D%81%E5%B9%B4%E6%BC%94%E8%BF%9B/</guid>
      <description>深入解析大语言模型文本生成的核心机制——解码策略。从基础的贪婪解码、束搜索，到温度采样、Top-k、Top-p，再到前沿的Min-p、Top-n-sigma等动态阈值方法，全面梳理这一领域二十年的技术演进，并深入探讨ICLR 2025热门论文Min-p采样的学术争议。</description>
    </item>
  </channel>
</rss>
