Related papers: The Gender Pay Gap Revisited with Big Data: Do Met…

Large multimodal models (LMMs) have revolutionized text-to-image generation, but they risk perpetuating the harmful social biases in their training data. Prior work has identified gender bias in these models, but methodological limitations…

Previous work has highlighted that existing post-hoc explanation methods exhibit disparities in explanation fidelity (across 'race' and 'gender' as sensitive attributes), and while a large body of work focuses on mitigating these issues at…

This study examines the use of Large Language Models (LLMs) for retrieving factual information, addressing concerns over their propensity to produce factually incorrect "hallucinated" responses or to altogether decline to even answer prompt…

Qualitative analysis of open-ended interviews plays a central role in ethnographic and economic research by uncovering individuals' values, motivations, and culturally embedded financial behaviors. While large language models (LLMs) offer…

We study the effect of tokenization on gender bias in machine translation, an aspect that has been largely overlooked in previous works. Specifically, we focus on the interactions between the frequency of gendered profession names in…

Addressing female underrepresentation in leadership positions has become a key policy objective. However, little is known about the extent to which leadership appeals differently to women. Collecting new data from a large firm, I document…

Information access research (and development) sometimes makes use of gender, whether to report on the demographics of participants in a user study, as inputs to personalized results or recommendations, or to make systems gender-fair,…

Economists disagree about the factors driving the substantial increase in residual wage inequality in the US over the past few decades. To identify changes in the returns to unobserved skills, we make a novel assumption about the dynamics…

Applications based on Machine Learning models have now become an indispensable part of the everyday life and the professional world. A critical question then recently arised among the population: Do algorithmic decisions convey any type of…

We investigate fairness dynamics during Large Language Model (LLM) training to enable the diagnoses of biases and mitigations through training interventions like early stopping; we find that biases can emerge suddenly and do not always…

The Fairness, Accountability, and Transparency in Machine Learning (FAT-ML) literature proposes a varied set of group fairness metrics to measure discrimination against socio-demographic groups that are characterized by a protected feature,…

The literature on the theme of gender differences in research performance indicates a quite evident gap in favor of men over women. Beyond the understanding of the factors that could be at the basis of this phenomenon, it is worthwhile…

With the growing use of ML in highly consequential domains, quantifying disparity with respect to protected attributes, e.g., gender, race, etc., is important. While quantifying disparity is essential, sometimes the needs of an occupation…

Regression-based predictive analytics used in modern kidney transplantation is known to inherit biases from training data. This leads to social discrimination and inefficient organ utilization, particularly in the context of a few social…

Large language models (LLMs) are increasingly used to assess moral or ethical statements, yet their judgments may reflect social and linguistic biases. This work presents a controlled, sentence-level study of how grammatical person, number,…

This report summarises the work and results produced at the 146th European Study Group with Industry/co-creation event with society on the challenge \textit{Breaking barriers for women in Science}. The aim of this challenge, proposed by the…

This paper introduces a framework for measuring how much black-box decision-makers rely on variables of interest. The framework adapts a permutation-based measure of variable importance from the explainable machine learning literature. With…

Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to…

Large Language Models (LLMs) are finding applications in all aspects of life, but their susceptibility to biases, particularly gender stereotyping, raises ethical concerns. This study introduces a novel methodology, a persona-based…

Although the gender gap in academia has narrowed, females are underrepresented within some fields in the USA. Prior research suggests that the imbalances between science, technology, engineering and mathematics fields may be partly due to…