Pith. sign in

REVIEW 4 cited by

Opportunities and Risks of LLMs for Scalable Deliberation with Polis

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 2306.11932 v1 pith:FGDNS34K submitted 2023-06-20 cs.SI cs.CLcs.CYcs.HC

classification cs.SIcs.CLcs.CYcs.HC
keywords llmspolisrisksopportunitiesdeliberativeintelligenceparticularresults
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Polis is a platform that leverages machine intelligence to scale up deliberative processes. In this paper, we explore the opportunities and risks associated with applying Large Language Models (LLMs) towards challenges with facilitating, moderating and summarizing the results of Polis engagements. In particular, we demonstrate with pilot experiments using Anthropic's Claude that LLMs can indeed augment human intelligence to help more efficiently run Polis conversations. In particular, we find that summarization capabilities enable categorically new methods with immense promise to empower the public in collective meaning-making exercises. And notably, LLM context limitations have a significant impact on insight and quality of these results. However, these opportunities come with risks. We discuss some of these risks, as well as principles and techniques for characterizing and mitigating them, and the implications for other deliberative or political systems that may employ LLMs. Finally, we conclude with several open future research directions for augmenting tools like Polis with LLMs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 20 citations worldwide. Full citation record

  1. A Roadmap to Impactful Pluralistic Alignment Research

    cs.AI 2026-07 accept novelty 6.0 of 10

    Pluralistic alignment research has produced no public evidence of adoption in deployed frontier models, so the field should focus on empirical justification, settled goals, and hill-climbable evaluations.

  2. Knowledge-guided Contextual Gene Set Analysis Using Large Language Models

    q-bio.GN 2025-06 conditional novelty 6.0 of 10

    cGSA combines gene clustering, enrichment analysis, and LLM filtering to prioritize contextually relevant pathways, beating g:Profiler, GPT-4o, and Llama baselines by over 30% on a new manually curated benchmark.

  3. Generative Social Choice: The Next Generation

    cs.GT 2025-05 conditional novelty 6.0 of 10

    The authors design a democratic process that uses approximate AI-driven queries to select a budget-limited slate of statements with provable approximate proportionality guarantees, and they test it with GPT-4o on real...

  4. Of the People, By the Algorithm: How AI Transforms Democratic Representation

    cs.CY 2025-08 unverdicted novelty 2.0 of 10

    AI will reshape representative democracy, pushing representatives toward architect roles for automated decision frameworks and hybrid systems of digital participation.

Pith tools