Various tools and practices have been developed to support practitioners in identifying,
assessing, and mitigating fairness-related harms caused by AI systems. However, prior …

Recent research suggests that predictions made by machine-learning models can amplify
biases present in the training data. When a model amplifies bias, it makes certain …

When a model's performance differs across socially or culturally relevant groups–like race,
gender, or the intersections of many such groups–it is often called” biased.” While much of …

We explore the extent to which zero-shot vision-language models exhibit gender bias for
different vision tasks. Vision models traditionally required task-specific labels for …

Predictive models for clinical outcomes that are accurate on average in a patient population
may underperform drastically for some subpopulations, potentially introducing or reinforcing …

A growing body of work uses the paradigm of algorithmic fairness to frame the development
of techniques to anticipate and proactively mitigate the introduction or exacerbation of health …

Generative AI systems produce a range of ethical and social risks. Evaluation of these risks
is a critical step on the path to ensuring the safety of these systems. However, evaluation …

Operationalizing AI fairness at LinkedIn's scale is challenging not only because there are
multiple mutually incompatible definitions of fairness but also because determining what is …

Objectives The American College of Cardiology and the American Heart Association
guidelines on primary prevention of atherosclerotic cardiovascular disease (ASCVD) …

When building NLP models, there is a tendency to aim for broader coverage, often
overlooking cultural and (socio) linguistic nuance. In this position paper, we make the case …