Betswish/MIRAGE

Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/

33
/ 100
Emerging

This project helps ensure the answers generated by AI models are accurate and directly supported by the provided source documents. You input a question, a set of relevant documents, and optionally, an AI-generated answer. It then outputs the AI's answer with clear links, or 'attributions,' showing exactly which parts of the answer came from which source documents. This is for AI developers, researchers, or anyone building or evaluating AI-powered question-answering systems.

No commits in the last 6 months.

Use this if you need to verify the factual accuracy and source-groundedness of AI-generated answers in your retrieval-augmented generation (RAG) applications.

Not ideal if you are looking for a general-purpose AI model for generating answers without needing detailed source attribution.

AI-powered Question Answering Generative AI AI Model Evaluation AI Explainability Natural Language Processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

26

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Mar 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/Betswish/MIRAGE"

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