Generative Social Choice: The Next Generation
This work addresses the challenge of summarizing unstructured opinions for democratic decision-making, but it is incremental as it builds on prior generative social choice frameworks.
The paper tackles the problem of generating concise slates of statements that proportionally represent user opinions in democratic processes, extending prior generative social choice frameworks with theoretical guarantees for approximate queries and length budgets. Using GPT-4o, it demonstrates effectiveness on city improvement and drug review datasets.
A key task in certain democratic processes is to produce a concise slate of statements that proportionally represents the full spectrum of user opinions. This task is similar to committee elections, but unlike traditional settings, the candidate set comprises all possible statements of varying lengths, and so it can only be accessed through specific queries. Combining social choice and large language models, prior work has approached this challenge through a framework of generative social choice. We extend the framework in two fundamental ways, providing theoretical guarantees even in the face of approximately optimal queries and a budget limit on the overall length of the slate. Using GPT-4o to implement queries, we showcase our approach on datasets related to city improvement measures and drug reviews, demonstrating its effectiveness in generating representative slates from unstructured user opinions.