mlsanityData to 14 Oct 2026

Opportunities and Risks of LLMs for Scalable Deliberation with Polis

arXiv 2306.11932 ↗First posted 20 Jun 2023cs.SI cs.CL cs.CYcited by 42

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 36 of its 86 references that are in the map. First posted on arXiv 20 Jun 2023.

Builds on

36 of 86 references.

References · 36

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  4. 2020Learning to summarize from human feedbackcited by 2,588
  5. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  7. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  8. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
  9. 2021Ethical and social risks of harm from Language Modelscited by 966
  10. 2019Attention is not Explanationcited by 929
  11. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  12. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 832
24 more
  1. 2023Whose Opinions Do Language Models Reflect?cited by 773
  2. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 729
  3. 2020SummEval: Re-evaluating Summarization Evaluationcited by 674
  4. 2019Attention is not not Explanationcited by 636
  5. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
  6. 2023Benchmarking Large Language Models for News Summarizationcited by 445
  7. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 380
  8. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 377
  9. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 301
  10. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 293
  11. 2019Measuring Bias in Contextualized Word Representationscited by 276
  12. 2022Predictability and Surprise in Large Generative Modelscited by 210
  13. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 207
  14. 2022Fine-tuning language models to find agreement among humans with diverse preferencescited by 189
  15. 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 189
  16. 2020Social Biases in NLP Models as Barriers for Persons with Disabilitiescited by 182
  17. 2021Annotating and Modeling Fine-grained Factuality in Summarizationcited by 131
  18. 2019Evaluating the Underlying Gender Bias in Contextualized Word Embeddingscited by 94
  19. 2022Evaluating Human-Language Model Interactioncited by 92
  20. 2021Detecting Hate Speech with GPT-3cited by 56
  21. 2023Language Models Trained on Media Diets Can Predict Public Opinioncited by 30
  22. 2022Spurious Correlations in Reference-Free Evaluation of Text Generationcited by 26
  23. 2022Birdwatch: Crowd Wisdom and Bridging Algorithms can Inform Understanding and Reduce the Spread of Misinformationcited by 21
  24. 2021Offensive Language and Hate Speech Detection with Deep Learning and Transfer Learningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 8; 2025: 15; 2026: 16.

42 papers.

Sort:

By area:

  1. 2023Generative Social Choicecited by 43
  2. 2025Emergence of polarization in networks of large language model agentscited by 26
  3. 2024Explaining Datasets in Words: Statistical Models with Natural Language Parameterscited by 21
  4. 2025Generative Social Choice: The Next Generationcited by 10
  5. 2024GeneAgent: Self-verification Language Agent for Gene Set Knowledge Discovery using Domain Databasescited by 9
  6. 2025Evaluation and Facilitation of Online Discussions in the LLM Era: A Surveycited by 9
  7. 2024Generative AI voting: fair collective choice is resilient to LLM biases and inconsistenciescited by 8
  8. 2025Benchmarking Overton Pluralism in LLMscited by 7
  9. 2023Leveraging Large Language Models for Collective Decision-Makingcited by 6
  10. 2024AI and the Future of Digital Public Squarescited by 6
  11. 2025Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMscited by 6
  12. 2023If the Sources Could Talk: Evaluating Large Language Models for Research Assistance in Historycited by 5
30 more
  1. 2024How will advanced AI systems impact democracy?cited by 5
  2. 2025Artificial Intelligence in Deliberation: The AI Penalty and the Emergence of a New Deliberative Dividecited by 4
  3. 2024Thoughtful Adoption of NLP for Civic Participation: Understanding Differences Among Policymakerscited by 3
  4. 2024LLMs as mediators: Can they diagnose conflicts accurately?cited by 3
  5. 2025Deliberate Lab: A Platform for Real-Time Human-AI Social Experimentscited by 3
  6. 2025Designing Synthetic Discussion Generation Systems: A Case Study for Online Facilitationcited by 2
  7. 2025PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectivescited by 2
  8. 2025Question the Questions: Auditing Representation in Online Deliberative Processescited by 2
  9. 2025The Variance Paradox: How AI Reduces Diversity but Increases Noveltycited by 1
  10. 2025An AI-Powered Framework for Analyzing Collective Idea Evolution in Deliberative Assembliescited by 1
  11. 2025Human-AI Narrative Synthesis to Foster Shared Understanding in Civic Decision-Makingcited by 1
  12. 2026Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voicecited by 1
  13. 2026Finding Common Ground in a Sea of Alternativescited by 1
  14. 2026Embeddings for Preferences, Not Semanticscited by 1
  15. 2026To Facilitate or not to Facilitate: Human and LLM Facilitator Tendencies in Online Discussionscited by 1
  16. 2024Estimating Contribution Quality in Online Deliberations Using a Large Language Modelcited by 0
  17. 2025Algorithmic Shortlisting in Participatory Budgetingcited by 0
  18. 2025Assessing the Political Fairness of Multilingual LLMs: A Case Study based on a 21-way Multiparallel EuroParl Datasetcited by 0
  19. 2026Can AI mediation improve democratic deliberation?cited by 0
  20. 2026The GDN-CC Dataset: Automatic Corpus Clarification for AI-enhanced Democratic Citizen Consultationscited by 0
  21. 2026Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Makingcited by 0
  22. 2026AI and Collective Decisions: Strengthening Legitimacy and Losers' Consentcited by 0
  23. 2026LLMs Should Incorporate Explicit Mechanisms for Human Empathycited by 0
  24. 2026"Taking Stock at FAccT": Using Participatory Design to Co-Create a Vision for the Fairness, Accountability and Transparency Communitycited by 0
  25. 2026Efficient Elicitation of Collective Disagreementscited by 0
  26. 2026Accountable Human-AI Deliberation with LLMs: Scaling Collective Intelligence through Symbiotic Scaffoldingcited by 0
  27. 2026Large Language Models are Perplexed by some Political Partiescited by 0
  28. 2026From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interactioncited by 0
  29. 2026New Conditions for Philosophers to Catch the Wave of Citizen Deliberation in the Age of Artificial Intelligence in advancecited by 0
  30. 2026AI Should Facilitate Democratic Deliberation at Scalecited by 0