Generative Social Choice: The Next Generation

Niclas Boehmer, Sara Fish, Ariel Procaccia

International Conference on Machine Learning 2025 · Oral

In an era increasingly shaped by digital discourse and the proliferation of diverse viewpoints, the challenge of accurately and proportionally summarizing collective opinion is paramount. This talk, "Generative Social Choice: The Next Generation," presented by Sara Fish, Niclas Boehmer, and Ariel Procaccia, addresses this complex problem by introducing a novel framework for **proportional summarization** of large, unstructured datasets of user opinions. The core objective is to generate a concise "slate" of statements that reflect the varying support levels across a user population, ensuring that an X fraction of users "control" an X fraction of the output. This has profound implications for applications in **AI and democracy**, where technologies are leveraged to enhance collective decision-making processes.

AI review

A competent and intellectually honest extension of prior work on generative social choice, introducing approximate proportionality guarantees that account for noisy LLM queries and demonstrating the approach empirically via a system called PROS. The core contribution — proving that proportionality degrades gracefully with query error, and showing near-optimality via matching impossibility results — is genuine theoretical work at the intersection of social choice and LLM systems. The framing is clean, the modularity insight is useful, and the impossibility results lend the guarantees real…