This repository curates a comprehensive list of research papers on Large Language Models (LLMs) in medicine, targeting researchers and practitioners interested in AI's application in healthcare. It provides a structured overview of LLMs' roles in medical research, clinical operations, and diagnostics, highlighting advancements in multimodal LLMs and autonomous healthcare agents.

How It Works

The repository functions as a living bibliography, systematically collecting and categorizing academic papers related to LLMs in the medical domain. It organizes research by sub-topics such as general-purpose LLMs in medicine, specialized medical LLMs, multimodal LLMs, LLM-powered healthcare agents, and evaluation strategies, facilitating targeted exploration of the field.

Quick Start & Requirements

This repository is a curated list of papers and does not require installation or execution. Links to papers, code, and demos are provided where available.

Highlighted Details

• Extensive coverage of specialized medical LLMs, including models like MEDITRON-70B, Taiyi, and HuatuoGPT-II.
• Detailed sections on multimodal LLMs in medicine, featuring research on vision-language models for radiology and pathology.
• A dedicated category for LLM-powered healthcare agents and autonomous systems.
• Compilation of evaluation strategies and benchmarks for assessing LLM performance in medical contexts.

Maintenance & Community

The project is maintained by Mingze Yuan, Peng Bao, and Zifan Chen, with contributions welcomed via pull requests and issue reports. The primary citation is for the review paper "Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review."

Licensing & Compatibility

This project is licensed under the MIT License, permitting broad use and compatibility.

Limitations & Caveats

The repository's scope is focused on the technological evolution of LLMs in medicine, and for clinical deployment insights, users are directed to the linked review paper.