OSU-NLP-Group/AttrScore

Code, datasets, models for the paper "Automatic Evaluation of Attribution by Large Language Models"

29
/ 100
Experimental

This project helps evaluate how well a large language model's (LLM) answer is supported by a given source text. You provide an LLM's claim (query + answer) and a reference document, and it tells you if the claim is Attributable, Extrapolatory, or Contradictory. Anyone working with LLMs who needs to verify the factual accuracy of their outputs against source material would find this useful.

No commits in the last 6 months.

Use this if you need to automatically and systematically assess the factual basis and trustworthiness of information generated by large language models.

Not ideal if you are looking for a tool to generate text or improve the fluency of an LLM's output, as this focuses on evaluation, not generation.

LLM-evaluation fact-checking content-verification AI-trustworthiness information-retrieval
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

56

Forks

2

Language

Python

License

MIT

Last pushed

Jul 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/OSU-NLP-Group/AttrScore"

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