Related papers: Gender differences in lying in sender-receiver gam…

Classifiers tend to propagate biases present in the data on which they are trained. Hence, it is important to understand how the demographic identities of the annotators of comments affect the fairness of the resulting model. In this paper,…

One of the most contested questions about human behaviour is whether there are inherent sex or gender differences in the formation and maintenance of social bonds. On one hand, female and male brains are structurally almost identical, and…

Large Language Models (LLMs) can generate biased responses. Yet previous direct probing techniques contain either gender mentions or predefined gender stereotypes, which are challenging to comprehensively collect. Hence, we propose an…

Previous experiments have found mixed results on whether honesty is intuitive or requires deliberation. Here we add to this literature by building on prior work of Capraro (2017). We report a large study (N=1,389) manipulating time pressure…

Sex and gender-based healthcare disparities contribute to differences in health outcomes. We focus on time to diagnosis (TTD) by conducting two large-scale, complementary analyses among men and women across 29 phenotypes and 195K patients.…

The evaluation and post-training of large language models (LLMs) rely on supervision, but strong supervision for difficult tasks is often unavailable, especially when evaluating frontier models. In such cases, models are demonstrated to…

This paper develops a peer effect model for count responses under rational expectations. The model accounts for heterogeneity in peer effects across groups based on observed characteristics. Identification is based on the linear model…

While several previous studies have analyzed gender bias in research, we are still missing a comprehensive analysis of gender differences in the AI community, covering diverse topics and different development trends. Using the AI Scholar…

Language Models have ushered a new age of AI gaining traction within the NLP community as well as amongst the general population. AI's ability to make predictions, generations and its applications in sensitive decision-making scenarios,…

Scientific retractions reflect issues within the scientific record, arising from human error or misconduct. Although gender differences in retraction rates have been previously observed in various contexts, no comprehensive study has…

As modern Large Language Models (LLMs) shatter many state-of-the-art benchmarks in a variety of domains, this paper investigates their behavior in the domains of ethics and fairness, focusing on protected group bias. We conduct a two-part…

Refusal behavior by Large Language Models is increasingly visible in content moderation, yet little is known about how refusals vary by the identity of the user making the request. This study investigates refusal as a sociotechnical outcome…

We consider a sender-receiver game in which the receiver's action is binary and the sender's preferences are state-independent. The state is multidimensional. The receiver can select one dimension of the state to check (i.e., observe)…

Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense. LLMs might "lie", for example, when instructed to output misinformation. Here, we develop a simple…

We study a disclosure game with a large evidence space. There is an unknown binary state. A sender observes a sequence of binary signals about the state and discloses a left truncation of the sequence to a receiver in order to convince him…

This paper is the first to explore the question of whether images that are classified incorrectly by a face analytics algorithm (e.g., gender classification) are any more or less likely to participate in an image pair that results in a face…

Gender bias in language models has attracted sufficient attention because it threatens social justice. However, most of the current debiasing methods degraded the model's performance on other tasks while the degradation mechanism is still…

This paper studies a communication game between an uninformed decision maker and two perfectly informed senders with conflicting interests. Senders can misreport information at a cost that increases with the size of the misrepresentation.…

Transparency and security are both central to Responsible AI, but they may conflict in adversarial settings. We investigate the strategic effect of transparency for agents through the lens of transferable adversarial example attacks. In…

Several previous studies have investigated user susceptibility to phishing attacks. A thorough meta-analysis or systematic review is required to gain a better understanding of these findings and to assess the strength of evidence for…