mims-harvard/KGARevion

KGARevion: AI Agent for Knowledge-Intensive Biomedical QA

35
/ 100
Emerging

Implements a multi-step verification pipeline that generates LLM-derived triplets and grounds them against PrimeKG using LoRA-finetuned models with pretrained entity/relation embeddings to filter hallucinations. Supports flexible backbone LLMs (Llama, etc.) with configurable revision rounds, and accommodates custom knowledge graphs and QA datasets through standardized data formats and retraining workflows.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

44

Forks

18

Language

Python

License

Last pushed

Mar 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/mims-harvard/KGARevion"

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