A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

XAI - An eXplainability toolbox for machine learning

Bias Auditing & Fair ML Toolkit

Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.

LangFair is a Python library for conducting use-case level LLM bias and fairness assessments

Automatic synthesis of RCTs

Toolkit for Auditing and Mitigating Bias and Fairness of Machine Learning Systems 🔎🤖🧰

Identify bias and measure fairness of your data

Bluetooth Impersonation AttackS (BIAS) [CVE 2020-10135]

A reading list and fortnightly discussion group designed to provoke discussion about ethical applications of, and processes for, data science.

A Python toolkit for analyzing machine learning models and datasets.

NeurIPS 2019 Paper: RUBi : Reducing Unimodal Biases for Visual Question Answering

Symmetric evaluation set based on the FEVER (fact verification) dataset

Compass-aligned Distributional Embeddings. Align embeddings from different corpora

A fairness library in PyTorch.

[CCKS 2021] On Robustness and Bias Analysis of BERT-based Relation Extraction

Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.

Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration

Bias correction method using quantile mapping