Awesome-LLM-Healthcare

Report Abuse

Basic Information

This repository is a curated anthology and living bibliography of research, code, and resources about large language models (LLMs) in medicine. It collects and organizes recent work on general-purpose and specialized medical LLMs, multimodal vision-language models, LLM-powered healthcare agents, and evaluation strategies. The README provides categorized sections that summarize papers and point to available implementations and demos when present. The project accompanies a review paper by the maintainers and is intended to track technical progress, integration challenges, and methodological advances rather than provide clinical deployment advice. It is structured to help readers navigate literature, surveys, datasets, benchmarks, and related repositories. The maintainers invite community contributions, issues, and pull requests and provide citation and license information for academic use.

Links

Categorization

App Details

Features
Comprehensive, categorized table of contents that groups entries into Specialized Medical LLMs, Multimodal LLMs, LLM-Powered Healthcare Agents, Evaluation, Related Surveys, and Repositories. Each entry lists recent papers with metadata such as date and venue and notes when code or demos are available. Dedicated subsections cover GPT-4V and multimodal efforts. The README includes a News section for notable updates, a BibTeX citation for the authors" review, maintainer and contributor contacts, acknowledgements, and an MIT license. The repository links to open-source implementations and related curated lists, and it emphasizes evaluative strategies and benchmarks for medical LLM performance and safety.
Use Cases
The repository helps researchers, practitioners, and students quickly discover state-of-the-art literature, open-source models, multimodal projects, and evaluation resources in medical LLMs. Its topical organization reduces search time for papers on diagnostics, radiology, multimodal vision-language systems, agent frameworks, and safety benchmarks. By indicating available code and related repositories, it supports project bootstrapping and reproducibility efforts. The included surveys, benchmarks, and evaluation strategies aid comparative analysis and method selection. The citation and license details facilitate academic referencing, and the open call for contributions enables the community to keep the list current as the field evolves.

Please fill the required fields*