Related papers: Testing for racial bias using inconsistent percept…

Previous generations of face recognition algorithms differ in accuracy for images of different races (race bias). Here, we present the possible underlying factors (data-driven and scenario modeling) and methodological considerations for…

We develop tools for utilizing correspondence experiments to detect illegal discrimination by individual employers. Employers violate US employment law if their propensity to contact applicants depends on protected characteristics such as…

Sample complexity of bias estimation is a lower bound on the runtime of any bias detection method. Many regulatory frameworks require the bias to be tested for all subgroups, whose number grows exponentially with the number of protected…

Much recent research has uncovered and discussed serious concerns of bias in facial analysis technologies, finding performance disparities between groups of people based on perceived gender, skin type, lighting condition, etc. These audits…

Face recognition algorithms, when used in the real world, can be very useful, but they can also be dangerous when biased toward certain demographics. So, it is essential to understand how these algorithms are trained and what factors affect…

In many domains, it is difficult to obtain the race data that is required to estimate racial disparity. To address this problem, practitioners have adopted the use of proxy methods which predict race using non-protected covariates. However,…

Studies have shown pulse oximeter measurements of blood oxygenation have statistical bias that is a function of race, which results in higher rates of occult hypoxemia, i.e., missed detection of dangerously low oxygenation, in patients of…

Accurately measuring discrimination is crucial to faithfully assessing fairness of trained machine learning (ML) models. Any bias in measuring discrimination leads to either amplification or underestimation of the existing disparity.…

Financial institutions increasingly rely on large language models (LLMs) for high-stakes decision-making. However, these models risk perpetuating harmful biases if deployed without careful oversight. This paper investigates racial bias in…

We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of intersectional biases…

Studies in bias and fairness in natural language processing have primarily examined social biases within a single language and/or across few attributes (e.g. gender, race). However, biases can manifest differently across various languages…

In this paper we look at popular fairness methods that use causal counterfactuals. These methods capture the intuitive notion that a prediction is fair if it coincides with the prediction that would have been made if someone's race, gender…

While the impact of social biases in language models has been recognized, prior methods for bias evaluation have been limited to binary association tests on small datasets, limiting our understanding of bias complexities. This paper…

The meteoric rise in text generation capability has been accompanied by parallel growth in interest in machine-generated text detection: the capability to identify whether a given text was generated using a model or written by a person.…

What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral.…

We propose an experimental method for measuring bias in face recognition systems. Existing methods to measure bias depend on benchmark datasets that are collected in the wild and annotated for protected (e.g., race, gender) and…

We tested whether and how biases in visual perception might influence motor actions. To do so, we designed an interception task in which subjects had to indicate the time when a moving object, whose trajectory was occluded, would reach a…

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 the work in algorithmic fairness over the last several…

Computer vision is widely deployed, has highly visible, society altering applications, and documented problems with bias and representation. Datasets are critical for benchmarking progress in fair computer vision, and often employ broad…

Although many fairness criteria have been proposed to ensure that machine learning algorithms do not exhibit or amplify our existing social biases, these algorithms are trained on datasets that can themselves be statistically biased. In…