Related papers: Quota-based debiasing can decrease representation …

Collective decision-making is a process by which a group of individuals determines a shared outcome that shapes societal dynamics; from innovation diffusion to organizational choices. A common approach to model these processes is using…

Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race invariant…

Societal biases present in pre-trained large language models are a critical issue as these models have been shown to propagate biases in countless downstream applications, rendering them unfair towards specific groups of people. Since…

Our society collects data on people for a wide range of applications, from building a census for policy evaluation to running meaningful clinical trials. To collect data, we typically sample individuals with the goal of accurately…

Representation bias is one of the most common types of biases in artificial intelligence (AI) systems, causing AI models to perform poorly on underrepresented data segments. Although AI practitioners use various methods to reduce…

We explore conclusions a person draws from observing society when he allows for the possibility that individuals' outcomes are affected by group-level discrimination. Injecting a single non-classical assumption, that the agent is…

Subset selection algorithms are ubiquitous in AI-driven applications, including, online recruiting portals and image search engines, so it is imperative that these tools are not discriminatory on the basis of protected attributes such as…

Artificial Intelligence (AI) finds widespread application across various domains, but it sparks concerns about fairness in its deployment. The prevailing discourse in classification often emphasizes outcome-based metrics comparing sensitive…

It is well known that women are underrepresented in the academic systems of many countries. Gender discrimination is one of the factors that could contribute to this phenomenon. This study considers a recent national academic recruitment…

Two typical forms of bias in user interaction data with recommender systems (RSs) are popularity bias and positivity bias, which manifest themselves as the over-representation of interactions with popular items or items that users prefer,…

Causal analysis may be affected by selection bias, which is defined as the systematic exclusion of data from a certain subpopulation. Previous work in this area focused on the derivation of identifiability conditions. We propose instead a…

We study a two-institution stable matching model in which candidates from two distinct groups are evaluated using partially correlated signals that are group-biased. This extends prior work (which assumes institutions evaluate candidates in…

Ranking functions that are used in decision systems often produce disparate results for different populations because of bias in the underlying data. Addressing, and compensating for, these disparate outcomes is a critical problem for fair…

Pre-trained language models trained on large-scale data have learned serious levels of social biases. Consequently, various methods have been proposed to debias pre-trained models. Debiasing methods need to mitigate only discriminatory bias…

The goal of group formation is to build a team to accomplish a specific task. Algorithms are employed to improve the effectiveness of the team so formed and the efficiency of the group selection process. However, there is concern that team…

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce…

Gender bias in language models has attracted sufficient attention because it threatens social justice. However, most of the current debiasing methods degraded the model's performance on other tasks while the degradation mechanism is still…

Societal biases that are contained in retrieved documents have received increased interest. Such biases, which are often prevalent in the training data and learned by the model, can cause societal harms, by misrepresenting certain groups,…

Biases with respect to socially-salient attributes of individuals have been well documented in evaluation processes used in settings such as admissions and hiring. We view such an evaluation process as a transformation of a distribution of…

Considerations of bias, fairness and representation are a prerequisite of responsible modern statistics. In statistical network analysis, observed networks are often incomplete or systematically biased, which can lead to systematic…