<?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>BioASQ on Abhijith Nagarajan</title><link>https://abhijith-nagarajan.com/tags/bioasq/</link><description>Recent content in BioASQ on Abhijith Nagarajan</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 19 Dec 2024 00:00:00 +0000</lastBuildDate><atom:link href="https://abhijith-nagarajan.com/tags/bioasq/index.xml" rel="self" type="application/rss+xml"/><item><title>SHERPA — Semi-Structured RAG (UIUC CS 546)</title><link>https://abhijith-nagarajan.com/projects/sherpa-semi-structured-rag/</link><pubDate>Thu, 19 Dec 2024 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/projects/sherpa-semi-structured-rag/</guid><description>A semi-structured, non-parametric memory framework for RAG that combines knowledge graphs with a hierarchical vector store. My contributions: Query Classification (heuristics → LLM-bootstrapped labels → fine-tuned BioLinkBERT) and Entity-Relation Extraction (REBEL fine-tuned on BioRED, with FastCoref preprocessing) — landed on REBEL after a long experimental funnel.</description></item></channel></rss>