Skip to main navigation Skip to search Skip to main content

Retrieval Augmented Generation: What Works and Lessons Learned

  • SUNY Buffalo
  • University of Pennsylvania
  • Department of Veterans Affairs

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Retrieval Augmented Generation has been shown to improve the output of large language models (LLMs) by providing context to the question or scenario posed to the model. We have tried a series of experiments to understand how best to improve the performance of the native models. We present the results of each of several experiments. These can serve as lessons learned for scientists looking to improve the performance of large language models for medical question answering tasks.

Original languageEnglish
Title of host publicationContext Sensitive Health Informatics
Subtitle of host publicationAI for Social Good - Proceedings of CSHI 2025
EditorsHadiza Ismaila, Linda Dusseljee-Peute, Romaric Marcilly, Peter L. Elkin, Craig E. Kuziemsky, Christian Nohr, Bethany A. Van Dort, Rebecca Randell
PublisherIOS Press BV
Pages2-6
Number of pages5
ISBN (Electronic)9781643685946
DOIs
StatePublished - May 12 2025
Event7th International Conference on Context Sensitive Health Informatics: AI for Social Good, CSHI 2025 - Bradford, United Kingdom
Duration: May 23 2025May 24 2025

Publication series

NameStudies in Health Technology and Informatics
Volume326
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

Conference7th International Conference on Context Sensitive Health Informatics: AI for Social Good, CSHI 2025
Country/TerritoryUnited Kingdom
CityBradford
Period05/23/2505/24/25

Keywords

  • Fine-Tuning
  • LLM
  • Prompt Engineering
  • RAG

Fingerprint

Dive into the research topics of 'Retrieval Augmented Generation: What Works and Lessons Learned'. Together they form a unique fingerprint.

Cite this