<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Knowledge Graphs | Vedaant Jain</title><link>https://vedaantjain.netlify.app/tags/knowledge-graphs/</link><atom:link href="https://vedaantjain.netlify.app/tags/knowledge-graphs/index.xml" rel="self" type="application/rss+xml"/><description>Knowledge Graphs</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Tue, 10 Sep 2024 00:00:00 +0000</lastBuildDate><image><url>https://vedaantjain.netlify.app/media/icon_hu68170e94a17a2a43d6dcb45cf0e8e589_3079_512x512_fill_lanczos_center_3.png</url><title>Knowledge Graphs</title><link>https://vedaantjain.netlify.app/tags/knowledge-graphs/</link></image><item><title>Quacer-C- Quantitative Certification of Knowledge Comprehension in LLMs</title><link>https://vedaantjain.netlify.app/project/quacer-c/</link><pubDate>Tue, 10 Sep 2024 00:00:00 +0000</pubDate><guid>https://vedaantjain.netlify.app/project/quacer-c/</guid><description>&lt;p>QuaCer-C is a framework for quantitatively certifying the knowledge comprehension capabilities of Large Language Models (LLMs). Using the structured nature of knowledge graphs, we are able to derive specifications for reasoning over unstructured data like text providing a way to formally understanding reasoning using exact confidence intervals.&lt;/p>
&lt;p>Authors: Isha Chaudhary, Vedaant Jain, Gagandeep Singh&lt;/p></description></item></channel></rss>