Related papers: Personalization Aids Pluralistic Alignment Under C…
In many prediction problems, the predictive model affects the distribution of the prediction target. This phenomenon is known as performativity and is often caused by the behavior of individuals with vested interests in the outcome of the…
Liability sharing and staffing jointly determine service quality in AI-assisted online medical consultation, yet their interaction is rarely examined in an integrated framework linking contracts to congestion via physician responses. This…
Dynamic, risk-based pricing can systematically exclude vulnerable consumer groups from essential resources such as health insurance and consumer credit. We show that a regulator can realign private incentives with social objectives through…
General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…
Artificial Intelligence based systems increasingly use personalization to provide users with relevant content, products, and solutions. Personalization is intended to support users and address their respective needs and preferences.…
In order to truly understand how social media might shape online discourses or contribute to societal polarization, we need refined models of platform choice, that is: models that help us understand why users prefer one social media…
Public AI benchmark results are widely broadcast by model developers as indicators of model quality within a growing and competitive market. However, these advertised scores do not necessarily reflect the traits of interest to those who…
The rise of foundation models has driven the emergence of AI supply chains, where upstream foundation model providers offer fine-tuning and inference services to downstream firms developing domain-specific applications. Downstream firms pay…
Despite the growing interest in collaborative AI, designing systems that seamlessly integrate human input remains a major challenge. In this study, we developed a task to systematically examine human preferences for collaborative agents. We…
AI (super) alignment describes the challenge of ensuring (future) AI systems behave in accordance with societal norms and goals. While a quickly evolving literature is addressing biases and inequalities, the geographic variability of…
AI-driven decision-making systems are becoming instrumental in the public sector, with applications spanning areas like criminal justice, social welfare, financial fraud detection, and public health. While these systems offer great…
We study the problem of online learning in competitive settings in the context of two-sided matching markets. In particular, one side of the market, the agents, must learn about their preferences over the other side, the firms, through…
We study a problem where wireless service providers compete for heterogenous wireless users. The users differ in their utility functions as well as in the perceived quality of service of individual providers. We model the interaction of an…
Large language model-based AI companions are increasingly viewed by users as friends or romantic partners, leading to deep emotional bonds. However, they can generate biased, discriminatory, and harmful outputs. Recently, users are taking…
Here we examine how AI agent "personalities" interact with human personalities to shape human-AI collaboration and performance. In a large-scale, preregistered randomized experiment, we paired 1,258 participants with AI agents prompted to…
Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model…
Recommendation algorithms typically build models based on historical user-item interactions (e.g., clicks, likes, or ratings) to provide a personalized ranked list of items. These interactions are often distributed unevenly over different…
Pluralistic alignment is typically operationalised as preference aggregation: producing responses that span (Overton), steer toward (Steerable), or proportionally represent (Distributional) diverse human values. We argue that aggregation…
Recent evidence, both in the lab and in the wild, suggests that the use of generative artificial intelligence reduces the diversity of content produced. The use of the same or similar AI models appears to lead to more homogeneous behavior.…
Generative Artificial Intelligence (AI) tools are rapidly adopted in the workplace and in education, yet the empirical evidence on AI's impact remains mixed. We propose a model of human-AI interaction to better understand and analyze…