Home /  Social Choice Seminar: Generative Social Choice


Social Choice Seminar: Generative Social Choice October 11, 2023 (10:30 AM PDT - 11:30 AM PDT)
Parent Program:
Location: SLMath: Baker Board Room, Online/Virtual
Speaker(s) Duane Cooper (Morehouse College), Paul Gölz (Harvard University)
Description No Description
Keywords and Mathematics Subject Classification (MSC)
Primary Mathematics Subject Classification No Primary AMS MSC
Secondary Mathematics Subject Classification No Secondary AMS MSC
No Video Uploaded

"Generative Social Choice" - Paul Gölz

Abstract: Traditionally, social choice theory has only been applicable to choices among a few predetermined alternatives but not to more complex decisions such as collectively selecting a textual statement. We introduce generative social choice, a framework that combines the mathematical rigor of social choice theory with large language models' capability to generate text and extrapolate preferences. This framework divides the design of AI-augmented democratic processes into two components: first, proving that the process satisfies rigorous representation guarantees when given access to oracle queries; second, empirically validating that these queries can be approximately implemented using a large language model. We illustrate this framework by applying it to the problem of generating a slate of statements that is representative of opinions expressed as free-form text, for instance in an online deliberative process. 

No Notes/Supplements Uploaded No Video Files Uploaded