@inproceedings{8b241cd4064341fcbf33298795918781,
title = "Retrieval Augmented Generation: What Works and Lessons Learned",
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.",
keywords = "Fine-Tuning, LLM, Prompt Engineering, RAG",
author = "Elkin, \{Peter L.\} and Guresh Mehta and Frank Lehouillier and Ross Koppel and Elkin, \{Aaron N.\} and Jonathan Nebeker and Brown, \{Steven H.\}",
note = "Publisher Copyright: {\textcopyright} 2025 The Authors.; 7th International Conference on Context Sensitive Health Informatics: AI for Social Good, CSHI 2025 ; Conference date: 23-05-2025 Through 24-05-2025",
year = "2025",
month = may,
day = "12",
doi = "10.3233/SHTI250225",
language = "English",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press BV",
pages = "2--6",
editor = "Hadiza Ismaila and Linda Dusseljee-Peute and Romaric Marcilly and Elkin, \{Peter L.\} and Kuziemsky, \{Craig E.\} and Christian Nohr and \{Van Dort\}, \{Bethany A.\} and Rebecca Randell",
booktitle = "Context Sensitive Health Informatics",
address = "Netherlands",
}