相关论文: Who Defines Fairness? Target-Based Prompting for D…

This paper studies long-term fair machine learning which aims to mitigate group disparity over the long term in sequential decision-making systems. To define long-term fairness, we leverage the temporal causal graph and use the…

Generative AI does not only replicate human creativity but also reproduces deep-seated cultural biases, making it crucial to critically examine how concepts like ugliness are understood and expressed by these tools. This study investigates…

Bias discovery is critical for black-box generative models, especiall text-to-image (TTI) models. Existing works predominantly focus on output-level demographic distributions, which do not necessarily guarantee concept representations to be…

Text-to-image (T2I) generative models have gained increased popularity in the public domain. While boasting impressive user-guided generative abilities, their black-box nature exposes users to intentionally- and intrinsically-biased…

Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data. Despite the high-quality generated faces, some minority groups can be rarely generated from the trained models due…

Machine learning models are extensively being used to make decisions that have a significant impact on human life. These models are trained over historical data that may contain information about sensitive attributes such as race, sex,…

In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework categorizes evaluations into two distinct groups: first,…

Fairness through Unawareness (FtU) describes the idea that discrimination against demographic groups can be avoided by not considering group membership in the decisions or predictions. This idea has long been criticized in the machine…

In many prediction problems, the predictive model affects the distribution of the prediction target. This phenomenon is known as performativity and is often caused by the behavior of individuals with vested interests in the outcome of the…

Classifiers are used throughout industry to enforce policies, ranging from the detection of toxic content to age-appropriate content filtering. While these classifiers serve important functions, it is also essential that they are built in…

Rankings of people and items has been highly used in selection-making, match-making, and recommendation algorithms that have been deployed on ranging of platforms from employment websites to searching tools. The ranking position of a…

Machine learning models often inherit biases from historical data, raising critical concerns about fairness and accountability. Conventional fairness interventions typically require access to sensitive attributes like gender or race, but…

As machine learning systems become increasingly integrated into human-centered domains such as healthcare, ensuring fairness while maintaining high predictive performance is critical. Existing bias mitigation techniques often impose a…

As AI-based decision systems proliferate, their successful operationalization requires balancing multiple desiderata: predictive performance, disparity across groups, safeguarding sensitive group attributes (e.g., race), and engineering…

With the aim of building machine learning systems that incorporate standards of fairness and accountability, we explore explicit subgroup sample complexity bounds. The work is motivated by the observation that classifier predictions for…

Algorithms learn rules and associations based on the training data that they are exposed to. Yet, the very same data that teaches machines to understand and predict the world, contains societal and historic biases, resulting in biased…

Text-to-image (T2I) models have rapidly advanced, enabling the generation of high-quality images from text prompts across various domains. However, these models present notable safety concerns, including the risk of generating harmful,…

Group bias in natural language processing tasks manifests as disparities in system error rates across texts authorized by different demographic groups, typically disadvantaging minority groups. Dataset balancing has been shown to be…

Machine learning models have achieved widespread success but often inherit and amplify historical biases, resulting in unfair outcomes. Traditional fairness methods typically impose constraints at the prediction level, without addressing…

We propose a novel algorithm for learning fair representations that can simultaneously mitigate two notions of disparity among different demographic subgroups in the classification setting. Two key components underpinning the design of our…