相关论文: Uncovering Name-Based Biases in Large Language Mod…

We study the presence of heteronormative biases and prejudice against interracial romantic relationships in large language models by performing controlled name-replacement experiments for the task of relationship prediction. We show that…

All AI models are susceptible to learning biases in data that they are trained on. For generative dialogue models, being trained on real human conversations containing unbalanced gender and race/ethnicity references can lead to models that…

As language models continue to be integrated into applications of personal and societal relevance, ensuring these models' trustworthiness is crucial, particularly with respect to producing consistent outputs regardless of sensitive…

This paper investigates the impact of using first names in Large Language Models (LLMs) and Vision Language Models (VLMs), particularly when prompted with ethical decision-making tasks. We propose an approach that appends first names to…

We employ an audit design to investigate biases in state-of-the-art large language models, including GPT-4. In our study, we prompt the models for advice involving a named individual across a variety of scenarios, such as during car…

Large language models (LLMs) acquire beliefs about gender from training data and can therefore generate text with stereotypical gender attitudes. Prior studies have demonstrated model generations favor one gender or exhibit stereotypes…

Large Language Models (LLMs) have become foundational in modern language-driven software applications, profoundly influencing daily life. A critical technique in leveraging their potential is role-playing, where LLMs simulate diverse roles…

Name-based gender prediction has traditionally categorized individuals as either female or male based on their names, using a binary classification system. That binary approach can be problematic in the cases of gender-neutral names that do…

Names are deeply tied to human identity. They can serve as markers of individuality, cultural heritage, and personal history. However, using names as a core indicator of identity can lead to over-simplification of complex identities. When…

Gender information is no longer a mandatory input when registering for an account at many leading Internet companies. However, prediction of demographic information such as gender and age remains an important task, especially in…

Computational social scientists often harness the Web as a "societal observatory" where data about human social behavior is collected. This data enables novel investigations of psychological, anthropological and sociological research…

A person's gender is a crucial piece of information when performing research across a wide range of scientific disciplines, such as medicine, sociology, political science, and economics, to name a few. However, in increasing instances,…

Social science research has shown that candidates with names indicative of certain races or genders often face discrimination in employment practices. Similarly, Large Language Models (LLMs) have demonstrated racial and gender biases in…

One critical aspect of building human-centered, trustworthy artificial intelligence (AI) systems is maintaining calibrated trust: appropriate reliance on AI systems outperforms both overtrust (e.g., automation bias) and undertrust (e.g.,…

Training data memorization in language models impacts model capability (generalization) and safety (privacy risk). This paper focuses on analyzing prompts' impact on detecting the memorization of 6 masked language model-based named entity…

Racial disparity in academia is a widely acknowledged problem. The quantitative understanding of racial based systemic inequalities is an important step towards a more equitable research system. However, because of the lack of robust…

Trustfulness -- one's general tendency to have confidence in unknown people or situations -- predicts many important real-world outcomes such as mental health and likelihood to cooperate with others such as clinicians. While data-driven…

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…

Through the use of first name substitution experiments, prior research has demonstrated the tendency of social commonsense reasoning models to systematically exhibit social biases along the dimensions of race, ethnicity, and gender (An et…

As large language models (LLMs) and LLM-based agents increasingly interact with humans in decision-making contexts, understanding the trust dynamics between humans and AI agents becomes a central concern. While considerable literature…