Retrieval Augmented Generation: What Works and Lessons Learned.

Journal: Studies in health technology and informatics
PMID: 40357591

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.

Authors

  • Peter L Elkin
    Department of Biomedical Informatics, University at Buffalo, Buffalo, NY.
  • Guresh Mehta
    Department of Biomedical Informatics, University at Buffalo.
  • Frank LeHouillier
    Department of Biomedical Informatics, University at Buffalo.
  • Ross Koppel
    University of Pennsylvania, Sociology Department, Philadelphia, Pennsylvania USA.
  • Aaron N Elkin
    Department of Biomedical Informatics, University at Buffalo.
  • Jonathan Nebeker
    U.S Department of Veteran Affairs, Office of Clinical Informatics, Washington DC USA.
  • Steven H Brown
    Office of Health Informatics, Department of Veterans Affairs.

Keywords

External Resources

Popular Topics
Recent Journals