15 datasets found

The COMPAS risk assessment dataset compiled by ProPublica, containing defendants' records of prison times, demographics, criminal histories, and the COMPAS risk scores.

A framework for defining fairness in machine learning.

A benchmark for assessing the performance of fairness mitigation methods in medical imaging.

A benchmark for assessing the performance of fairness mitigation methods in computer vision.

A new benchmark for assessing the performance of cross-domain learning approaches for unfairness mitigation in computer vision.

Two binary classification tasks with binary protected attributes: emoji prediction and occupation classification.

A dataset for measuring affective normalization of outcome mappings.

Language Agency Classification (LAC) dataset for training accurate language agency classifiers.

Language Agency Bias Evaluation (LABE) framework to systematically and comprehensively measure gender, racial, and intersectional biases in language agency across a wide scope...

A crowdsourced dataset for studying differences in fairness preferences depending on demographic identities.

HONEST is a fairness dataset specifically designed to assess LMs' outputs' hurtfulness.

FAIRBELIEF is a language-agnostic analytical approach to capture and assess beliefs embedded in LMs.

The BIOS dataset is a biography classification dataset with 28 profession classes and 4 intersectional demographic groups (male-wealthy, male-rest, female-wealthy, female-rest).

A recent study FairSeg proposes the first fairness dataset for medical segmentation, including 10,000 SLO fundus images from 10,000 patients with pixel-wise disc and cup...

Fairness is an important topic for medical image analysis, driven by the challenge of unbalanced training data among diverse target groups and the societal demand for equitable...