This event is organized by the Schwartz Reisman Institute for Technology and Society.
Note: Event details may change. Please refer to the Schwartz Reisman Institute for Technology and Society’s events page for the most current information.
Our weekly SRI Seminar Series welcomes Kate Larson, professor and University Research Chair in the Cheriton School of Computer Science at the University of Waterloo and a research scientist at Google DeepMind. Larson’s work sits at the intersection of artificial intelligence, multi-agent systems, and decision-making, with a particular interest in how intelligent systems interact, coordinate, and cooperate.
Talk title:
“Who decides what AI values? New frontiers in fair and diverse alignment”
Abstract:
As large language models (LLMs) become central to public discourse and decision-making, we face a critical policy challenge: whose values should these systems reflect? Current AI training methods typically average out human feedback into a single "one-size-fits-all" model. This approach can silence minority voices, fails to handle conflicting cultural norms, and ignores the basic democratic principles we use to govern human societies. In this talk, we explore formal frameworks for pluralistic alignment, moving beyond monolithic reward models toward formal aggregation mechanisms.
Moderator: Nisarg Shah, Department of Computer Science
Location: Online
Suggested reading:
Ali Falahati, Mohammad Mohammadi Amiri, Kate Larson, Lukasz Golab “The alignment game: A theory of long-horizon alignment through recursive generation,” arXiv, to appear in AAAI 2026.
Carter Blair and Kate Larson, “Generating fair consensus statements with social choice on token-level MDPs,” arXiv, to appear in AAMAS 2026.
Roberto-Rafael Maura-Rivero, Marc Lanctot, Francesco Visin, Kate Larson, “Jackpot! Alignment as a maximal lottery,” 2025.
Carter Blair, Kate Larson, Edith Law, “Reflective verbal reward design for pluralistic alignment,” IJCAI 2025.
About Kate Larson
Kate Larson is a professor and holds a University Research Chair in the Cheriton School of Computer Science, University of Waterloo and is a research scientist with Google DeepMind. She is interested in algorithmic questions arising in artificial intelligence and multiagent systems with a particular focus on algorithmic game theory and computational social choice, group decision making, preference modelling, and the insights that reinforcement learning can bring to these problems, along with ways of promoting and supporting cooperative AI.
She is an AAAI Fellow, and her work has been awarded several best paper awards, including at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), and ACM Conference on Computer-Supported Cooperative Work and Social Computing (ACM CSCW). Because she likes seeing cooperation in action, she has been involved in organizing and supporting many conferences and workshops in different roles, including AAMAS (general chair) and IJCAI (program chair).
About the SRI Seminar Series
The SRI Seminar Series brings together the Schwartz Reisman community and beyond for a robust exchange of ideas that advance scholarship at the intersection of technology and society. Seminars are led by a leading or emerging scholar and feature extensive discussion.
Each week, a featured speaker will present for 45 minutes, followed by an open discussion. Registered attendees will be emailed a Zoom link before the event begins. The event will be recorded and posted online.