SquareResearchCenter-AI/BEExAI
Benchmark to Evaluate EXplainable AI
When you're working with machine learning models and need to understand *why* they make certain predictions, BEExAI helps you systematically evaluate different 'explainable AI' methods. It takes your existing tabular dataset and trained machine learning models, then quantifies how well various explanation techniques reveal the model's decision-making process. This tool is designed for AI practitioners, researchers, or anyone building and deploying models who needs to ensure their explanations are reliable and trustworthy.
No commits in the last 6 months. Available on PyPI.
Use this if you need a standardized way to compare and benchmark different 'explainable AI' (XAI) methods for tabular data and various machine learning models to pick the best one for your use case.
Not ideal if you're looking for an explanation method to integrate directly into an application without needing to compare its performance against others.
Stars
20
Forks
2
Language
Python
License
BSD-3-Clause
Last pushed
Mar 14, 2025
Commits (30d)
0
Dependencies
13
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SquareResearchCenter-AI/BEExAI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...