Back to search

Institutional Repository of Vilnius University

Hybrid retrieval methods and an attention mechanism in medical retrieval-augmented generation systems /

Abstract

dc:description

This thesis evaluates information retrieval methods for medical document collections in a retrieval­augmented generation (RAG) setting. Clinical guideline documents were preprocessed to extract text, tables and images into a unified textual format, and multiple retrieval strategies were implemented and compared. Experimental results showed that dense semantic retrieval alone provides limited accuracy (33%), while subunit­based scoring improves early ranks (42%) and hybrid semantic­lexical retrieval achieves the strongest performance (88%). Native sparse attention reranking did not yield meaningful improvements, when trained with a small subset of question­answer pairs (35%).

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Braun, Ugnius Byron,

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
eng

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Braun, Ugnius Byron,. Hybrid retrieval methods and an attention mechanism in medical retrieval-augmented generation systems /. Institutional Repository of Vilnius University, 2026. https://repository.vu.lt/VU:ELABAETD277678336&prefLang=en_US