<?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>Preference Inference on Cognaptus</title>
    <link>https://cognaptus.com/tags/preference-inference/</link>
    <description>Recent content in Preference Inference on Cognaptus</description>
    <generator>Hugo -- 0.145.0</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 11 Aug 2025 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://cognaptus.com/tags/preference-inference/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>From Ballots to Budgets: Can LLMs Be Trusted as Social Planners?</title>
      <link>https://cognaptus.com/blog/2025-08-11-from-ballots-to-budgets-can-llms-be-trusted-as-social-planners/</link>
      <pubDate>Mon, 11 Aug 2025 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2025-08-11-from-ballots-to-budgets-can-llms-be-trusted-as-social-planners/</guid>
      <description>A mechanism-first reading of how participatory budgeting turns LLM resource allocation into a test of preference inference, constraint discipline, and operational trust.</description>
    </item>
    <item>
      <title>Love in the Time of Context: Why LLMs Still Don&#39;t Get You</title>
      <link>https://cognaptus.com/blog/2025-08-05-love-in-the-time-of-context-why-llms-still-dont-get-you/</link>
      <pubDate>Tue, 05 Aug 2025 00:00:00 +0000</pubDate>
      <guid>https://cognaptus.com/blog/2025-08-05-love-in-the-time-of-context-why-llms-still-dont-get-you/</guid>
      <description>Cupid shows that LLM personalization fails less because models cannot write tailored answers and more because they retrieve, infer, and apply the wrong contextual preference.</description>
    </item>
  </channel>
</rss>
