<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:wfw="http://wellformedweb.org/CommentAPI/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:slash="http://purl.org/rss/1.0/modules/slash/" xmlns:memo="https://memo.d.foundation/ns/feed/1">
  <channel>
    <title>evaluation - Dwarves Memo</title>
    <atom:link href="https://memo.d.foundation/topics/applied-llm/tags/evaluation/rss.xml" rel="self" type="application/rss+xml" />
    <link>https://memo.d.foundation/topics/applied-llm/tags/evaluation</link>
    <description>The newest notes tagged evaluation on Dwarves Memo.</description>
    <lastBuildDate>Fri, 04 Oct 2024 00:00:00 GMT</lastBuildDate>
    <language>en-US</language>
    <sy:updatePeriod>hourly</sy:updatePeriod>
    <sy:updateFrequency>1</sy:updateFrequency>
    <item>
      <title>LLM as a judge</title>
      <link>https://memo.d.foundation/llm/llm-as-a-judge</link>
      <pubDate>Fri, 04 Oct 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[nnhuyhoang]]></dc:creator>
      <description><![CDATA[With the robust growth of LLM models currently, there is a new method is used to evaluate the performance of large language models (LLMs): LLM-as-a-Judge, also known as LLM-evaluators. This approach take adavantages of other advanced language models to assess the quality and effectiveness of responses generated by other LLMs.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/llm-as-a-judge</guid>
    </item>
    <item>
      <title>Evaluation guidelines for LLM applications, part 1: the evaluation checklist</title>
      <link>https://memo.d.foundation/llm/evaluation-guideline-for-llm-application</link>
      <pubDate>Thu, 26 Sep 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[datnguyennnx]]></dc:creator>
      <description><![CDATA[A product evaluation checklist and the business and user expectations to settle before integrating a third-party LLM into an application.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/evaluation-guideline-for-llm-application</guid>
    </item>
    <item>
      <title>Evaluation guidelines for LLM applications, part 2: types of evaluation and considerations</title>
      <link>https://memo.d.foundation/llm/llm-evaluation-types-and-considerations</link>
      <pubDate>Thu, 26 Sep 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[datnguyennnx]]></dc:creator>
      <description><![CDATA[The difference between model evaluations and product evaluations, plus coverage, monitoring, user feedback and when fine-tuning is needed.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/llm-evaluation-types-and-considerations</guid>
    </item>
    <item>
      <title>Evaluating search engine in RAG systems</title>
      <link>https://memo.d.foundation/llm/hybrid-search</link>
      <pubDate>Thu, 08 Aug 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[datnguyennnx]]></dc:creator>
      <description><![CDATA[Hybrid search comes to solving problems in vector search and full-text search. Let's see how it works. In this article, we will know how hybrid search approach and how to evaluate each search method through metrics in information retrieval.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/hybrid-search</guid>
    </item>
  </channel>
</rss>