Version 1
: Received: 20 October 2024 / Approved: 22 October 2024 / Online: 22 October 2024 (11:17:55 CEST)
How to cite:
Youssef, H.; Turner, J.; Sanders, E. Retrieval-Augmented Medical Large Language Models. Preprints2024, 2024101658. https://doi.org/10.20944/preprints202410.1658.v1
Youssef, H.; Turner, J.; Sanders, E. Retrieval-Augmented Medical Large Language Models. Preprints 2024, 2024101658. https://doi.org/10.20944/preprints202410.1658.v1
Youssef, H.; Turner, J.; Sanders, E. Retrieval-Augmented Medical Large Language Models. Preprints2024, 2024101658. https://doi.org/10.20944/preprints202410.1658.v1
APA Style
Youssef, H., Turner, J., & Sanders, E. (2024). Retrieval-Augmented Medical Large Language Models. Preprints. https://doi.org/10.20944/preprints202410.1658.v1
Chicago/Turabian Style
Youssef, H., Jacob Turner and Evan Sanders. 2024 "Retrieval-Augmented Medical Large Language Models" Preprints. https://doi.org/10.20944/preprints202410.1658.v1
Abstract
Biomedical large language models (LLMs) have made significant strides, but their reliance on external retrieval mechanisms presents challenges in accuracy and computational efficiency. To address these issues, we propose MedRAG-Refine, a generative LLM designed specifically for the biomedical domain. Our model integrates a two-stage fine-tuning process, incorporating a self-reflection mechanism to improve reasoning quality. We evaluate our model on MedQA, MedMCQA, and MMLU datasets, demonstrating superior performance over state-of-the-art methods. Additionally, human evaluations confirm the enhanced accuracy and reasoning quality of our model in real-world medical tasks.
Keywords
Biomedical Language Models; Self-Reflection Mechanism; Medical Question-Answering;Retrieval-Augmented Models
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.