dccuchile/wefe
WEFE: The Word Embeddings Fairness Evaluation Framework. WEFE is a framework that standardizes the bias measurement and mitigation in Word Embeddings models. Please feel welcome to open an issue in case you have any questions or a pull request if you want to contribute to the project!
Provides a unified interface for multiple fairness metrics (WEAT, RNSB, RIPA) and encapsulates test words into reusable "query" objects for standardized evaluation across embedding models. Implements bias mitigation through a scikit-learn-style ``fit-transform`` pipeline that separates transformation calculation from execution. Integrates with gensim, scikit-learn, and PyTorch-compatible embeddings with comprehensive metric and debiasing method implementations.
183 stars. Available on PyPI.
Stars
183
Forks
14
Language
Python
License
MIT
Category
Last pushed
Nov 24, 2025
Commits (30d)
0
Dependencies
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/dccuchile/wefe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
dreji18/Fairness-in-AI
Detecting Bias and ensuring Fairness in AI solutions
amazon-science/bold
Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language...
dhfbk/variationist
Variationist: Exploring Multifaceted Variation and Bias in Written Language Data (ACL 2024 demo track)
microsoft/SafeNLP
Safety Score for Pre-Trained Language Models
soarsmu/BiasFinder
BiasFinder | IEEE TSE | Metamorphic Test Generation to Uncover Bias for Sentiment Analysis Systems