Related papers: Seeing Stereotypes
Discrimination can occur when the underlying unbiased labels are overwritten by an agent with potential bias, resulting in biased datasets that unfairly harm specific groups and cause classifiers to inherit these biases. In this paper, we…
Insider threats (InTs) within organizations are small in number but have a disproportionate ability to damage systems, information, and infrastructure. Existing InT research studies the problem from psychological, technical, and educational…
Institutions widely use student evaluations to assess the faculty's teaching performance, but underlying trends and biases can influence their interpretation. Using data from Rate My Professors, we conduct the largest and most recent…
It is evident that deep text classification models trained on human data could be biased. In particular, they produce biased outcomes for texts that explicitly include identity terms of certain demographic groups. We refer to this type of…
Recent advances in machine learning leverage massive datasets of unlabeled images from the web to learn general-purpose image representations for tasks from image classification to face recognition. But do unsupervised computer vision…
Bias can be introduced in diverse ways in machine learning datasets, for example via selection or label bias. Although these bias types in themselves have an influence on important aspects of fair machine learning, their different impact…
This research introduces the Multilevel Embedding Association Test (ML-EAT), a method designed for interpretable and transparent measurement of intrinsic bias in language technologies. The ML-EAT addresses issues of ambiguity and difficulty…
Mitigating algorithmic bias is a critical task in the development and deployment of machine learning models. While several toolkits exist to aid machine learning practitioners in addressing fairness issues, little is known about the…
International Large-scale Assessments (ILSAs), such as the Program for International Student Assessment (PISA) and the Trends in International Mathematics and Science Study (TIMSS), are cornerstone tools for global educational research and…
AI technologies that sense student attention and emotions to enable more personalised teaching interventions are increasingly promoted, but raise pressing questions about student learning, well-being, and ethics. In particular, students'…
Language serves as a powerful tool for the manifestation of societal belief systems. In doing so, it also perpetuates the prevalent biases in our society. Gender bias is one of the most pervasive biases in our society and is seen in online…
Fairness in machine learning seeks to mitigate model bias against individuals based on sensitive features such as sex or age, often caused by an uneven representation of the population in the training data due to selection bias. Notably,…
Standard benchmarks of bias and fairness in large language models (LLMs) measure the association between the user attributes stated or implied by a prompt and the LLM's short text response, but human-AI interaction increasingly requires…
Stereotypes, bias, and discrimination have been extensively documented in Machine Learning (ML) methods such as Computer Vision (CV) [18, 80], Natural Language Processing (NLP) [6], or both, in the case of large image and caption models…
Current bias evaluations in Instruction Text-to-Speech (ITTS) often rely on univariate testing, overlooking the compositional structure of social cues. In this work, we investigate gender bias by modeling prompts as combinations of Social…
Stereotypes are generalized beliefs about groups of people, which are used to make decisions and judgments about them. Although such heuristics can be useful when decisions must be made quickly, or when information is lacking, they can also…
Theory of Mind (ToM) in Large Language Models (LLMs) refers to the model's ability to infer the mental states of others, with failures in this ability often manifesting as systemic implicit biases. Assessing this challenge is difficult, as…
AI-based systems such as language models have been shown to replicate and even amplify social biases reflected in their training data. Among other questionable behaviors, this can lead to AI-generated text--and text suggestions--that…
Spurious correlations are everywhere. While humans often do not perceive them, neural networks are notorious for learning unwanted associations, also known as biases, instead of the underlying decision rule. As a result, practitioners are…
Item Response Theory (IRT) models aim to assess latent abilities of $n$ examinees along with latent difficulty characteristics of $m$ test items from categorical data that indicates the quality of their corresponding answers. Classical…