MedEmbed large v0.1 EU AI Act Compliance Profile

MedEmbed: Specialized Embedding Model for Medical and Clinical Information Retrieval

Model Description

MedEmbed is a family of embedding models fine-tuned specifically for medical and clinical data, designed to enhance performance in healthcare-related natural language processing (NLP) tasks, particularly information retrieval.

GitHub Repo: https://github.com/abhinand5/MedEmbed

Technical Blog Post: https://huggingface.co/blog/abhinand/medembed-finetuned-embedding-models-for-medical-ir

Intended Use

This model is intended for use in medical and clinical contexts to improve information retrieval, question answering, and semantic search tasks. It can be integrated into healthcare systems, research tools, and medical literature databases to enhance search capabilities and information access.

Training Data

The model was trained using a simple yet effective synthetic data generation pipeline:

1. Source: Clinical notes from PubMed Central (PMC)
2. Processing: LLaMA 3.1 70B model used to generate query-response pairs
3. Augmentation: Negative sampling for challenging examples
4. Format: Triplets (query, positive response, negative response) for contrastive learning

Performance

MedEmbed consistently outperforms general-purpose embedding models across various medical NLP benchmarks:

• ArguAna
• MedicalQARetrieval
• NFCorpus
• PublicHealthQA
• TRECCOVID

Specific performance metrics (nDCG, MAP, Recall, Precision, MRR) are available in the full documentation.

Limitations

While highly effective for

Your obligations as a MedEmbed large v0.1 deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages

Library

Base Model