RSSE: Ivan Soraperra (Center for Human and Machines of the Max Planck Institute for Human Development) Effectiveness and Fragility of LLM Apologies

It is our pleasure that Ivan Soraperra (Center for Human and Machines of the Max Planck Institute for Human Development) will present on Thursday, March 26, 2026, at 12:45 in room RB437 about the topic “Effectiveness and Fragility of LLM Apologies”.

Registration is not required and anyone who would like to attend is warmly invited.

It is also possible to participate online via MS Teams at this link. In case of any connection issues, please contact lubomir.cingl@vse.cz.

ABSTRACT: Apologies are a core social mechanism for repairing trust after transgressions. With the increasing availability of large language models (LLMs), individuals can now outsource the writing of apologies, potentially altering both their content and social meaning. In online experiments, this paper studies how LLM-generated apologies differ from human apologies, how they are evaluated, and whether individuals anticipate these differences when choosing how to apologize.

BIO: Ivan Soraperra is Senior Research Scientist at the Center for Humans and Machines at the Max Planck Institute for Human Development in Berlin. His research lies at the intersection of behavioral and experimental economics, with a focus on human–AI interaction, algorithm-mediated communication, and ethical decision-making. He studies how AI tools influence preferences, trust, rule compliance, and social behavior. His work has been published in leading journals, including The Review of Economics and Statistics, Proceedings of the National Academy of Sciences, Nature Human Behaviour, and Games and Economic Behavior. He previously held positions at the University of Amsterdam (CREED), Leiden University, and the University of Verona. He earned his Ph.D. in Economics and Management from the University of Trento.