Related papers: Auditing ML Models for Individual Bias and Unfairn…

Statistical fairness stipulates equivalent outcomes for every protected group, whereas causal fairness prescribes that a model makes the same prediction for an individual regardless of their protected characteristics. Counterfactual data…

Pre-trained transformer-based language models are becoming increasingly popular due to their exceptional performance on various benchmarks. However, concerns persist regarding the presence of hidden biases within these models, which can…

Despite the high interest for Machine Learning (ML) in academia and industry, many issues related to the application of ML to real-life problems are yet to be addressed. Here we put forward one limitation which arises from a lack of…

With the growing adoption of machine learning (ML) systems in areas like law enforcement, criminal justice, finance, hiring, and admissions, it is increasingly critical to guarantee the fairness of decisions assisted by ML. In this paper,…

With an increased focus on incorporating fairness in machine learning models, it becomes imperative not only to assess and mitigate bias at each stage of the machine learning pipeline but also to understand the downstream impacts of bias…

Fairness audits of institutional risk models are critical for understanding how deployed machine learning pipelines allocate resources. Drawing on multi-year collaboration with Centennial College, where our prior ethnographic work…

Methods for interpreting machine learning black-box models increase the outcomes' transparency and in turn generates insight into the reliability and fairness of the algorithms. However, the interpretations themselves could contain…

Bias in Foundation Models (FMs) - trained on vast datasets spanning societal and historical knowledge - poses significant challenges for fairness and equity across fields such as healthcare, education, and finance. These biases, rooted in…

Algorithmic risk assessments are increasingly used to help humans make decisions in high-stakes settings, such as medicine, criminal justice and education. In each of these cases, the purpose of the risk assessment tool is to inform…

Machine learning models are trained to find patterns in data. NLP models can inadvertently learn socially undesirable patterns when training on gender biased text. In this work, we propose a general framework that decomposes gender bias in…

A number of applications (e.g., AI bot tournaments, sports, peer grading, crowdsourcing) use pairwise comparison data and the Bradley-Terry-Luce (BTL) model to evaluate a given collection of items (e.g., bots, teams, students, search…

Large Language Models (LLMs) used in creative workflows can reinforce stereotypes and perpetuate inequities, making fairness auditing essential. Existing methods rely on constrained tasks and fixed benchmarks, leaving open-ended creative…

Fair inference in supervised learning is an important and active area of research, yielding a range of useful methods to assess and account for fairness criteria when predicting ground truth targets. As shown in recent work, however, when…

Numerous multimodal misinformation benchmarks exhibit bias toward specific modalities, allowing detectors to make predictions based solely on one modality. While previous research has quantified bias at the dataset level or manually…

Bias auditing of language models (LMs) has received considerable attention as LMs are becoming widespread. As such, several benchmarks for bias auditing have been proposed. At the same time, the rapid evolution of LMs can make these…

Item Response Theory (IRT) has been widely used in educational psychometrics to assess student ability, as well as the difficulty and discrimination of test questions. In this context, discrimination specifically refers to how effectively a…

Fairness in machine learning (ML) has garnered significant attention in recent years. While existing research has predominantly focused on the distributive fairness of ML models, there has been limited exploration of procedural fairness.…

The increasing usage of new data sources and machine learning (ML) technology in credit modeling raises concerns with regards to potentially unfair decision-making that rely on protected characteristics (e.g., race, sex, age) or other…

Recent studies show that Natural Language Processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality. To create interventions and mitigate these biases…

Recently, there has been a rising awareness that when machine learning (ML) algorithms are used to automate choices, they may treat/affect individuals unfairly, with legal, ethical, or economic consequences. Recommender systems are…