Pith. sign in

REVIEW 5 cited by

Generative Social Choice

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2309.01291 v3 pith:JIHWX6NN submitted 2023-09-03 cs.GT cs.AIcs.LG

classification cs.GTcs.AIcs.LG
keywords choicesocialdemocraticprocessdesignframeworkgenerativeguarantees
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The mathematical study of voting, social choice theory, has traditionally only been applicable to choices among a few predetermined alternatives, but not to open-ended decisions such as collectively selecting a textual statement. We introduce generative social choice, a design methodology for open-ended democratic processes that combines the rigor of social choice theory with the capability of large language models to generate text and extrapolate preferences. Our framework divides the design of AI-augmented democratic processes into two components: first, proving that the process satisfies representation guarantees when given access to oracle queries; second, empirically validating that these queries can be approximately implemented using a large language model. We apply this framework to the problem of summarizing free-form opinions into a proportionally representative slate of opinion statements; specifically, we develop a democratic process with representation guarantees and use this process to portray the opinions of participants in a survey about abortion policy. In a trial with 100 representative US residents, we find that 84 out of 100 participants feel "excellently" or "exceptionally" represented by the slate of five statements we extracted.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CALMA: A Process for Deriving Context-aligned Axes for Language Model Alignment

    cs.CY 2025-07 conditional novelty 6.0 of 10

    CALMA is a grounded-theory, participatory method for deriving community-specific language model alignment axes from open-ended user interactions and group discussion, piloted with two small groups.

  2. Emergence of human-like polarization among large language model agents

    cs.SI 2025-01 conditional novelty 6.0 of 10

    Interacting LLM agents form homophilic networks and polarized opinions that mirror human echo-chamber and backfire effects, with individual-level interventions reducing polarization most.

  3. Data Sharing with a Generative AI Competitor

    cs.GT 2025-05 conditional novelty 5.0 of 10

    In a two-stage data-sharing game, the unique equilibrium is either that the firm shares just enough data to stop the platform buying expert data, or that the firm shares an amount that maximizes its payoff while the p...

  4. Designing for Constructive Civic Communication: A Framework for Human-AI Collaboration in Community Engagement Processes

    cs.HC 2025-05 conditional novelty 5.0 of 10

    The paper adapts Shneiderman's human-AI framework to civic communication by splitting human control into public leader and community organization control, and offers design considerations for constructive engagement.

  5. AI and the Future of Digital Public Squares

    cs.CY 2024-12 unverdicted novelty 3.0 of 10

    A multi-stakeholder agenda argues that LLM-enabled collective dialogue, bridging, moderation, and proof-of-humanity tools can strengthen digital public squares if paired with research and safeguards.

Pith tools