<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Prompt on Peng Tan's AI Blog</title><link>https://c44db530.hobbytp-github-io.pages.dev/zh/tags/prompt/</link><description>一个关注 AI 各领域的专题博客</description><atom:link href="https://c44db530.hobbytp-github-io.pages.dev/zh/tags/prompt/index.xml" rel="self" type="application/rss+xml"/><item><title>Verbalized Sampling: 言语采样提升模型多样性</title><link>https://c44db530.hobbytp-github-io.pages.dev/zh/papers/verbalize_sampling/</link><pubDate>Mon, 27 Oct 2025 20:22:48 +0800</pubDate><guid>https://c44db530.hobbytp-github-io.pages.dev/zh/papers/verbalize_sampling/</guid><description>Verbalized Sampling: 言语采样提升模型多样性</description></item><item><title>Meta: 提示词对决优化器 (PDO)</title><link>https://c44db530.hobbytp-github-io.pages.dev/zh/papers/prompt_duel_optimizer/</link><pubDate>Sun, 26 Oct 2025 20:22:48 +0800</pubDate><guid>https://c44db530.hobbytp-github-io.pages.dev/zh/papers/prompt_duel_optimizer/</guid><description>这篇由Meta和宾夕法尼亚州立大学的研究者发布的论文提出了一种创新的、无需人工标注数据的提示词优化方法。</description></item></channel></rss>