BBQ
Bias detector
A dataset and benchmarking framework to evaluate the performance of question answering models on detecting and mitigating social biases.
Repository for the Bias Benchmark for QA dataset.
92 stars
8 watching
22 forks
Language: Python
last commit: over 2 years agoRelated projects:
| Repository | Description | Stars |
|---|---|---|
 modeloriented/fairmodels | A tool for detecting bias in machine learning models and mitigating it using various techniques. | 86 |
 algofairness/blackboxauditing | A software package for auditing and analyzing machine learning models to detect unfair biases | 130 |
 privacytrustlab/bias_in_fl | This project investigates how bias can be introduced and spread in machine learning models during federated learning, and aims to detect and mitigate this issue. | 11 |
 dssg/aequitas | Toolkit to audit and mitigate biases in machine learning models | 701 |
 i-gallegos/fair-llm-benchmark | Compiles bias evaluation datasets and provides access to original data sources for large language models | 115 |
 13o-bbr-bbq/machine_learning_security | An open-source project that explores the intersection of machine learning and security to develop tools for detecting vulnerabilities in web applications. | 1,987 |
 ethicalml/xai | An eXplainability toolbox for machine learning that enables data analysis and model evaluation to mitigate biases and improve performance | 1,135 |
 megantosh/fairness_measures_code | This repository contains implementations of measures to quantify discrimination in data | 38 |
 iamgroot42/mimir | A Python package for measuring memorization in Large Language Models. | 126 |
 freedomintelligence/mllm-bench | Evaluates and compares the performance of multimodal large language models on various tasks | 56 |
 responsiblyai/responsibly | A toolkit for auditing and mitigating bias in machine learning systems | 96 |
 seldonio/alibi-detect | A Python library for detecting outliers, adversarial examples, and data drift in various types of data | 2,262 |
 visionjo/facerec-bias-bfw | This project provides a data proxy to evaluate bias in facial recognition systems across demographic groups. | 47 |
| nyu-mll/glue-baselines | An implementation of multi-task learning approaches to learning sentence representations for the GLUE benchmark | 779 |
 cisco-open/inclusive-language | Tools and resources for identifying biased language in code and content. | 21 |