Related papers: Seeing Stereotypes
Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these…
Deep neural networks are efficient at learning the data distribution if it is sufficiently sampled. However, they can be strongly biased by non-relevant factors implicitly incorporated in the training data. These include operational biases,…
Scoring models support decision-making in financial institutions. Their estimation and evaluation are based on the data of previously accepted applicants with known repayment behavior. This creates sampling bias: the available labeled data…
As machine learning-enabled Text-to-Image (TTI) systems are becoming increasingly prevalent and seeing growing adoption as commercial services, characterizing the social biases they exhibit is a necessary first step to lowering their risk…
Assessment of proficiency of the learner is an essential part of Intelligent Tutoring Systems (ITS). We use Item Response Theory (IRT) in computer-aided language learning for assessment of student ability in two contexts: in test sessions,…
Models of computational trust support users in taking decisions. They are commonly used to guide users' judgements in online auction sites; or to determine quality of contributions in Web 2.0 sites. However, most existing systems require…
Motivated by the goals of dataset pruning and defect identification, a growing body of methods have been developed to score individual examples within a dataset. These methods, which we call "example difficulty scores", are typically used…
Large language models (LLMs) can serve as judges that offer rapid and reliable assessments of other LLM outputs. However, models may systematically assign overly favorable ratings to their own outputs, a phenomenon known as self-bias, which…
Recent research has highlighted the high incidence of errors in spreadsheet models used in industry. In an attempt to reduce the incidence of such errors, a teaching approach has been devised which aids students to reduce their likelihood…
A critical problem in deep learning is that systems learn inappropriate biases, resulting in their inability to perform well on minority groups. This has led to the creation of multiple algorithms that endeavor to mitigate bias. However, it…
Estimating the confidence of disparity maps inferred by a stereo algorithm has become a very relevant task in the years, due to the increasing number of applications leveraging such cue. Although self-supervised learning has recently spread…
Accurately quantifying children's social interaction behavior is part of understanding their cognitive and emotional development, as well as mental health conditions. Kids-SIT is a web-based tool designed to computationally analyze…
Media coverage has a substantial effect on the public perception of events. Nevertheless, media outlets are often biased. One way to bias news articles is by altering the word choice. The automatic identification of bias by word choice is…
Text-to-Image (T2I) models have transformed visual content creation, producing highly realistic images from natural language prompts. However, concerns persist around their potential to replicate and magnify existing societal biases. To…
We present a simple but effective method to measure and mitigate model biases caused by reliance on spurious cues. Instead of requiring costly changes to one's data or model training, our method better utilizes the data one already has by…
Machine learning models that convert user-written text descriptions into images are now widely available online and used by millions of users to generate millions of images a day. We investigate the potential for these models to amplify…
Minority college students face unique challenges shaped by their identities based on their gender/sexual orientation, race, religion, and academic institutions, which influence their academic and social experiences. Although research has…
Large language models (LLMs) have garnered significant attention for their remarkable performance in a continuously expanding set of natural language processing tasks. However, these models have been shown to harbor inherent societal…
The widespread adoption of Artificial Intelligence (AI) in K-12 education highlights the need for psychometrically-tested measures of teachers' AI literacy. Existing work has primarily relied on either self-report (SR) or objective-based…
Over the past two decades, the notion of implicit bias has come to serve as an important component in our understanding of discrimination in activities such as hiring, promotion, and school admissions. Research on implicit bias posits that…