<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Python | Shaoyang Cui</title><link>https://spidermonk7.github.io/tags/python/</link><atom:link href="https://spidermonk7.github.io/tags/python/index.xml" rel="self" type="application/rss+xml"/><description>Python</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Fri, 01 Nov 2024 00:00:00 +0000</lastBuildDate><image><url>https://spidermonk7.github.io/media/icon_hu7729264130191091259.png</url><title>Python</title><link>https://spidermonk7.github.io/tags/python/</link></image><item><title>FAB - Factory of Abstract-style Benchmark</title><link>https://spidermonk7.github.io/project/fab/</link><pubDate>Fri, 01 Nov 2024 00:00:00 +0000</pubDate><guid>https://spidermonk7.github.io/project/fab/</guid><description>&lt;p>Developed the first fully automated, low-cost benchmark generation framework for abstract-style evaluation across general-purpose domains. Enables scalable testing of large language models using structured abstraction errors, covering semantic, structural, and factual variants.
Repository: &lt;a href="https://github.com/spidermonk7/FAB-Benchmark" target="_blank" rel="noopener">https://github.com/spidermonk7/FAB-Benchmark&lt;/a>&lt;/p></description></item></channel></rss>