microsoft/LoNLI

Testing Diverse Reasoning of NLI Systems

35
/ 100
Emerging

This project provides a comprehensive test suite to evaluate how well Natural Language Inference (NLI) systems understand different types of reasoning. You input a large set of test cases designed to probe 17 specific reasoning abilities, and it helps you analyze your NLI system's performance on each. Researchers and developers working on NLI models use this to thoroughly assess and improve their models' understanding of nuances in language.

No commits in the last 6 months.

Use this if you need to systematically test and analyze the diverse reasoning capabilities of your Natural Language Inference (NLI) models, going beyond simple accuracy metrics.

Not ideal if you are looking for a pre-trained NLI model or a general-purpose dataset for training your NLI system from scratch.

natural-language-inference NLP-model-testing reasoning-evaluation AI-model-diagnostics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

10

Forks

3

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 28, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/microsoft/LoNLI"

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