Retrieval Augmented Generation: What Works and Lessons Learned
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250225 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Peter L Elkin und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, University at Buffalo. Hauptthemen laut MEDLINE: Natural Language Processing, Information Storage and Retrieval. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Informatics, University at Buffalo.
- Office of Health Informatics, Department of Veterans Affairs.
- Faculty of Engineering, University of Southern Denmark.
- University of Pennsylvania.
Zitieren
APA
Elkin, P. L., Mehta, G., LeHouillier, F., Koppel, R., Elkin, A. N., Nebeker, J., & Brown, S. H. (2025). Retrieval Augmented Generation: What Works and Lessons Learned. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250225
Vancouver
Elkin PL, Mehta G, LeHouillier F, Koppel R, Elkin AN, Nebeker J, et al. Retrieval Augmented Generation: What Works and Lessons Learned. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250225
BibTeX
@article{Elkin2025,
author = {Elkin, Peter L and Mehta, Guresh and LeHouillier, Frank and Koppel, Ross and Elkin, Aaron N and Nebeker, Jonathan and Brown, Steven H},
title = {Retrieval Augmented Generation: What Works and Lessons Learned},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250225}
}
EUVIMED