Bias Python Packages

interpret-core

Fit interpretable models. Explain blackbox machine learning.

interpret

Fit interpretable models. Explain blackbox machine learning.

aif360

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.

langfair

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

debiai-gui

DebiAI easy start module, the standalone version of DebiAI

xai

XAI - An eXplainability toolbox for machine learning

nlpguard

NLPGuard: A Framework for Mitigating the use of Protected Attributes in NLP

risk-of-bias

Software and AI for Risk of Bias assessment.

dbias

Detect, Recognize and de-bias textual data.

daindex

Deterioration Allocation Index Framework

insurance-fairness

Proxy discrimination auditing, discrimination-free pricing, and fairness diagnostics for UK insurance pricing models under FCA Consumer Duty and Equality Act 2010.

aequitas-lite

Bias Auditing & Fair ML Toolkit

explainx

Explain & debug any blackbox machine learning model with a single line of code.

dnikit

A Python toolkit for analyzing machine learning models and datasets.

powerlift

Interactive Benchmarking for Machine Learning.

cade

Compass-aligned Distributional Embeddings. Align embeddings from different corpora

fmm-fairness-eval

Foundation Model for Medicine — fairness/bias evaluation CLI for medical AI (research)

ai-bias-detect

A repository including a comparison between Google's What If Bias tool and fairdetect by Ryan Daher with some added improvements

equalityml

Evidence-based tools and community collaboration to end algorithmic bias, one data scientist at a time.

ytdebunk

This project aims to automate the extraction of MP3 audio from a given YouTube video link, transcribe the audio content, and analyze the transcriptions using Agentic AI to identify logical fallacies and incorrect claims made by YouTubers.

dnikit-tensorflow

A Python toolkit for analyzing machine learning models and datasets.

privyfilter

Privy filter is made to give the method for removing/accommodating for unethical bias in data.

fair-detect-group-a

A repository including a comparison between Google's What If Bias tool and fairdetect by Ryan Daher with some added improvements

dnikit-torch

A Python toolkit for analyzing machine learning models and datasets.