Carnegie Mellon University

Block Center for Technology and Society

Block Center for Technology and Society › Responsible AI › Research › Bias, Unfairness, and Discrimination

Responsible AI Research

Bias, Unfairness, and Discrimination

Defining, measuring, and remedying harmful disparities produced as the result of introducing AI in high-stakes decision.

2022

A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms

Akpinar, Heidari, Wu, Zhu, et al (2022)

How Child Welfare Workers Reduce Racial Disparities in Algorithmic Decisions

Kawakami, Holstein, Wu, et al. (2022)

Prior Record Score, Disparate Impact, & Recidivism in Pennsylvania

Nagin (2022)

2021

Characterizing Fairness Over the Set of Good Models Under Selective Labels

Coston, Chouldechova, et al. (2021)

Discovering and Validating AI Errors With Crowdsourced Failure Reports

Hong, Cabrera, et al. (2021)

Empirical Observation of Negligible Fairness-Accuracy Trade-Offs in Machine Learning for Public Policy

Ghani et al. (2021)

2020

Counterfactual Risk Assessments, Evaluation, and Fairness

Coston, Chouldechova, et al. (2020)

2019

A Moral Framework for Understanding Fair ML through Economic Models of Equality of Opportunity

Heidari et al. (2019)

Artificial Intelligence and Black-Box Medical Decisions: Accuracy versus Explainability

London (2019)

Fair Transfer Learning with Missing Protected Attributes

Coston et al. (2019)

Improving Fairness in Machine Learning Systems: What Do Industry Practitioners Need?

Holstein, et al. (2019)

Visual Analytics for Discovering Intersectional Bias in Machine Learning

Cabrera et al. (2019)

Pre-2019

Social Justice-Oriented Interaction Design: Outlining Key Design Strategies and Commitments

Fox, et al. (2016)

Contact us | ResponsibleAI@cmu.edu