While research on applications and evaluations of explanation methods continues to expand, fairness of the explanation methods concerning disparities in their performance across subgroups remains an often overlooked aspect. In this paper, we address this gap by showing that, across three tasks and five language models, widely used post-hoc feature attribution methods exhibit significant gender disparity with respect to their faithfulness, robustness, and complexity. These disparities persist even when the models are pre-trained or fine-tuned on particularly unbiased datasets, indicating that the disparities we observe are not merely consequences of biased training data. Our results highlight the importance of addressing disparities in explanations when developing and applying explainability methods, as these can lead to biased outcomes against certain subgroups, with particularly critical implications in high-stakes contexts. Furthermore, our findings underscore the importance of incorporating the fairness of explanations, alongside overall model fairness and explainability, as a requirement in regulatory frameworks.

Automated Face Recognition Systems (FRSs), developed using deep learning models, are deployed worldwide for identity verification and facial attribute analysis. The performance of these models is determined by a complex interdependence among the model architecture, optimization/loss function and datasets. Although FRSs have surpassed human-level accuracy, they continue to be disparate against certain demographics. Due to the ubiquity of applications, it is extremely important to understand the impact of the three components -- model architecture, loss function and face image dataset on the accuracy-disparity trade-off to design better, unbiased platforms. In this work, we perform an in-depth analysis of three FRSs for the task of gender prediction, with various architectural modifications resulting in ten deep-learning models coupled with four loss functions and benchmark them on seven face datasets across 266 evaluation configurations. Our results show that all three components have an individual as well as a combined impact on both accuracy and disparity. We identify that datasets have an inherent property that causes them to perform similarly across models, independent of the choice of loss functions. Moreover, the choice of dataset determines the model's perceived bias -- the same model reports bias in opposite directions for three gender-balanced datasets of ``in-the-wild'' face images of popular individuals. Studying the facial embeddings shows that the models are unable to generalize a uniform definition of what constitutes a ``female face'' as opposed to a ``male face'', due to dataset diversity. We provide recommendations to model developers on using our study as a blueprint for model development and subsequent deployment.

This study addresses the persistent challenges of Workplace Gender Equality (WGE) in Indonesia, examining regional disparities in gender empowerment and inequality through the Gender Empowerment Index (IDG) and Gender Inequality Index (IKG). Despite Indonesia's economic growth and incremental progress in gender equality, as indicated by improvements in the IDG and IKG scores from 2018 to 2023, substantial regional differences remain. Utilizing k-means clustering, the study identifies two distinct clusters of regions with contrasting gender profiles. Cluster 0 includes regions like DKI Jakarta and Central Java, characterized by higher gender empowerment and lower inequality, while Cluster 1 comprises areas such as Papua and North Maluku, where gender disparities are more pronounced. The analysis reveals that local socio-economic conditions and governance frameworks play a critical role in shaping regional gender dynamics. Correlation analyses further demonstrate that higher empowerment is generally associated with lower inequality and greater female representation in professional roles. These findings underscore the importance of targeted, region-specific interventions to promote WGE, addressing both structural and cultural barriers. The insights provided by this study aim to guide policymakers in developing tailored strategies to foster gender equality and enhance women's participation in the workforce across Indonesia's diverse regions.

Expanding the involvement of women in Science, Technology, Engineering, and Mathematics (STEM) across Latin America is crucial for economic advancement, social equity, and global competitiveness; however, these efforts have proven to be challenging. Women in the region are underrepresented in STEM10 and even more so in leadership positions.17,18 The limited availability of current information and the difficulties associated with obtaining reliable data to mitigate gender disparities create difficulties in implementing policies to reduce the gender gap in STEM. Researchers, organizations, and policymakers working to reduce the gender gap need access to dependable data to understand the root causes of gender disparities, promote evidence-based interventions, and increase accountability and transparency. In the quest for solutions to these challenges, an international research network between Bolivia, Brazil, and Peru, "Equality in Leadership for Latin America STEM" (ELLAS), emerged in 2022.6

Gender bias in text corpora used in various natural language processing (NLP) contexts, such as for training large language models (LLMs), can lead to the perpetuation and amplification of societal inequalities. This is particularly pronounced in gendered languages like Spanish or French, where grammatical structures inherently encode gender, making the bias analysis more challenging. Existing methods designed for English are inadequate for this task due to the intrinsic linguistic differences between English and gendered languages. This paper introduces a novel methodology that leverages the contextual understanding capabilities of LLMs to quantitatively analyze gender representation in Spanish corpora. By utilizing LLMs to identify and classify gendered nouns and pronouns in relation to their reference to human entities, our approach provides a nuanced analysis of gender biases. We empirically validate our method on four widely-used benchmark datasets, uncovering significant gender disparities with a male-to-female ratio ranging from 4:1 to 6:1. These findings demonstrate the value of our methodology for bias quantification in gendered languages and suggest its application in NLP, contributing to the development of more equitable language technologies.

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 at all. Specifically, it investigates the presence of gender-based biases in LLMs' responses to factual inquiries. This paper takes a multi-pronged approach to evaluating GPT models by evaluating fairness across multiple dimensions of recall, hallucinations and declinations. Our findings reveal discernible gender disparities in the responses generated by GPT-3.5. While advancements in GPT-4 have led to improvements in performance, they have not fully eradicated these gender disparities, notably in instances where responses are declined. The study further explores the origins of these disparities by examining the influence of gender associations in prompts and the homogeneity in the responses.

Generative AI models like DALL-E 2 can interpret textual prompts and generate high-quality images exhibiting human creativity. Though public enthusiasm is booming, systematic auditing of potential gender biases in AI-generated images remains scarce. We addressed this gap by examining the prevalence of two occupational gender biases (representational and presentational biases) in 15,300 DALL-E 2 images spanning 153 occupations, and assessed potential bias amplification by benchmarking against 2021 census labor statistics and Google Images. Our findings reveal that DALL-E 2 underrepresents women in male-dominated fields while overrepresenting them in female-dominated occupations. Additionally, DALL-E 2 images tend to depict more women than men with smiling faces and downward-pitching heads, particularly in female-dominated (vs. male-dominated) occupations. Our computational algorithm auditing study demonstrates more pronounced representational and presentational biases in DALL-E 2 compared to Google Images and calls for feminist interventions to prevent such bias-laden AI-generated images to feedback into the media ecology.

The study of biases, such as gender or racial biases, is an important topic in the social and behavioural sciences. However, the literature does not always clearly define the concept. Definitions of bias are often ambiguous or not provided at all. To study biases in a precise manner, it is important to have a well-defined concept of bias. We propose to define bias as a direct causal effect that is unjustified. We propose to define the closely related concept of disparity as a direct or indirect causal effect that includes a bias. Our proposed definitions can be used to study biases and disparities in a more rigorous and systematic way. We compare our definitions of bias and disparity with various criteria of fairness introduced in the artificial intelligence literature. We also illustrate our definitions in two case studies, focusing on gender bias in science and racial bias in police shootings. Our proposed definitions aim to contribute to a better appreciation of the causal intricacies of studies of biases and disparities. We hope that this will also promote an improved understanding of the policy implications of such studies.

AI may have sexist tendencies. But, sorry, the problem is still us humans. Amazon recently scrapped an employee recruiting algorithm plagued with problems, according to a report from Reuters. Ultimately, the applicant screening algorithm did not return relevant candidates, so Amazon canned the program. But in 2015, Amazon had a more worrisome issue with this AI: it was down-ranking women.

In July 2017, Google engineer James Damore distributed a memorandum titled "Google's Ideological Echo Chamber," which was critical of Google's diversity policies. The memo "went viral" and was widely distributed inside and outside of Google, leading to extensive media discussions. In August 2017, Google fired Damore for violation of the company's code of conduct. The U.S. National Labor Relations Board concluded that Google did not violate U.S. federal labor law when it fired Damore, but Damore filed a lawsuit against Google for discrimination. The memo's central argument was that the gender disparity observed in the tech industry in general, and in Google in particular, could be partially explained by biological differences between women and men.