Related papers: Studying the Transfer of Biases from Programmers t…

Safely deploying machine learning models to the real world is often a challenging process. Models trained with data obtained from a specific geographic location tend to fail when queried with data obtained elsewhere, agents trained in a…

Programming languages development has intensified in recent years. New ones are created; new features, often cross-paradigm, are featured in old ones. This new programming landscape makes language selection a more complex decision, both…

Despite substantial research efforts evaluating how well large language models~(LLMs) handle global cultural diversity, the mechanisms behind their cultural knowledge acquisition, particularly in multilingual settings, remain unclear. We…

As LLMs are increasingly integrated into user-facing applications, addressing biases that perpetuate societal inequalities is crucial. While much work has gone into measuring or mitigating biases in these models, fewer studies have…

Metaphors are pervasive in communication, making them crucial for natural language processing (NLP). Previous research on automatic metaphor processing predominantly relies on training data consisting of English samples, which often reflect…

Large language models (LLMs) are able to engage in natural-sounding conversations with humans, showcasing unprecedented capabilities for information retrieval and automated decision support. They have disrupted human-technology interaction…

Assessments of algorithmic bias in large language models (LLMs) are generally catered to uncovering systemic discrimination based on protected characteristics such as sex and ethnicity. However, there are over 180 documented cognitive…

Agentic systems increasingly rely on language models to monitor their own behavior. For example, coding agents may self critique generated code for pull request approval or assess the safety of tool-use actions. We show that this design…

An inductive learning algorithm takes a set of data as input and generates a hypothesis as output. A set of data is typically consistent with an infinite number of hypotheses; therefore, there must be factors other than the data that…

Large language models are increasingly used in decision-making tasks that require them to process information from a variety of sources, including both human experts and other algorithmic agents. How do LLMs weigh the information provided…

Machine learning software is increasingly being used to make decisions that affect people's lives. But sometimes, the core part of this software (the learned model), behaves in a biased manner that gives undue advantages to a specific group…

We develop a structural econometric model to capture the decision dynamics of human evaluators on an online micro-lending platform, and estimate the model parameters using a real-world dataset. We find two types of biases in gender,…

Predictive modeling is increasingly being employed to assist human decision-makers. One purported advantage of replacing human judgment with computer models in high stakes settings-- such as sentencing, hiring, policing, college admissions,…

System prompts in Large Language Models (LLMs) are predefined directives that guide model behaviour, taking precedence over user inputs in text processing and generation. LLM deployers increasingly use them to ensure consistent responses…

Understanding human behaviour, neuroscience and psychology using concepts from the domain of AI is increasing in popularity. Given the massive integration of AI technologies into our daily lives, AI-related concepts are being used to…

Numerous works have noted similarities in how machine learning models represent the world, even across modalities. Although much effort has been devoted to uncovering properties and metrics on which these models align, surprisingly little…

Movies reflect society and also hold power to transform opinions. Social biases and stereotypes present in movies can cause extensive damage due to their reach. These biases are not always found to be the need of storyline but can creep in…

Sentiment analysis (SA) systems are widely deployed in many of the world's languages, and there is well-documented evidence of demographic bias in these systems. In languages beyond English, scarcer training data is often supplemented with…

Despite the benefits of personalizing items and information tailored to users' needs, it has been found that recommender systems tend to introduce biases that favor popular items or certain categories of items, and dominant user groups. In…

The increasing deployment of artificial intelligence (AI) tools to inform decision making across diverse areas including healthcare, employment, social benefits, and government policy, presents a serious risk for disabled people, who have…