richard-peng-xia/RULE

[EMNLP'24] RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models

33
/ 100
Emerging

This project helps medical professionals and researchers improve the factual accuracy of AI models that answer questions based on medical images and related text. You provide medical images (like X-rays) and questions about them, and it produces more reliable answers by ensuring the AI's responses align with established medical facts. Medical AI researchers and practitioners focused on diagnostic support or medical education would use this.

No commits in the last 6 months.

Use this if you are developing or using AI models for medical imaging tasks and need to ensure their responses are factually accurate and trustworthy.

Not ideal if your primary goal is general image analysis outside of the medical domain, or if you don't require high-stakes factual accuracy from your vision-language models.

medical-imaging clinical-decision-support medical-AI-development radiology-reporting healthcare-AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

98

Forks

5

Language

Python

License

MIT

Last pushed

Dec 13, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/richard-peng-xia/RULE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.