Generative Social Choice: The Next Generation

TL;DR

This paper advances generative social choice by integrating large language models with theoretical guarantees, enabling the creation of representative opinion slates under query and length constraints, demonstrated through practical city and drug review datasets.

Contribution

It extends the generative social choice framework to handle approximate queries and length budgets, providing theoretical guarantees and practical implementation with GPT-4o.

Findings

Effective generation of representative opinion slates

Theoretical guarantees under query and length constraints

Successful application on real-world datasets

Abstract

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.