mlsanityData to 7 Oct 2026

Plurals: A System for Guiding LLMs Via Simulated Social Ensembles

arXiv 2409.17213 ↗First posted 25 Sep 2024cs.CL cs.AI cs.CYcited by 17

Not on the map. Why?

Abstract (arXiv)

Recent debates raised concerns that language models may favor certain viewpoints. But what if the solution is not to aim for a 'view from nowhere' but rather to leverage different viewpoints? We introduce Plurals, a system and Python library for pluralistic AI deliberation. Plurals consists of Agents (LLMs, optionally with personas) which deliberate within customizable Structures, with Moderators overseeing deliberation. Plurals is a generator of simulated social ensembles. Plurals integrates with government datasets to create nationally representative personas, includes deliberation templates inspired by deliberative democracy, and allows users to customize both information-sharing structures and deliberation behavior within Structures. Six case studies demonstrate fidelity to theoretical constructs and efficacy. Three randomized experiments show simulated focus groups produced output resonant with an online sample of the relevant audiences (chosen over zero-shot generation in 75% of trials). Plurals is both a paradigm and a concrete system for pluralistic AI. The Plurals library is available at https://github.com/josh-ashkinaze/plurals and will be continually updated.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 51 of its 138 references that are in the map. First posted on arXiv 25 Sep 2024.

Builds on

51 of 138 references.

References · 51

  1. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  3. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  4. 2023Towards Understanding Sycophancy in Language Modelscited by 988
  5. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  6. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  7. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  8. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 452
  9. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  10. 2018AI safety via debatecited by 384
  11. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 380
  12. 2021AI and the Everything in the Whole Wide World Benchmarkcited by 340
38 more
  1. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 329
  2. 2021Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotationscited by 306
  3. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
  4. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 255
  5. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 229
  6. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
  7. 2023Does Writing with Language Models Reduce Content Diversity?cited by 190
  8. 2024A Roadmap to Pluralistic Alignmentcited by 175
  9. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 116
  10. 2022Jury Learning: Integrating Dissenting Voices into Machine Learning Modelscited by 115
  11. 2024Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communitiescited by 84
  12. 2023MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledgecited by 62
  13. 2023When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviourcited by 61
  14. 2023On the steerability of large language models toward data-driven personascited by 53
  15. 2024Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debatecited by 48
  16. 2024Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulationcited by 46
  17. 2023Writer-Defined AI Personas for On-Demand Feedback Generationcited by 36
  18. 2023Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuningcited by 28
  19. 2018A Survey of Word Embeddings Evaluation Methodscited by 26
  20. 2024Building Better AI Agents: A Provocation on the Utilisation of Persona in LLM-based Conversational Agentscited by 26
  21. 2020Between Subjectivity and Imposition: Power Dynamics in Data Annotation for Computer Visioncited by 25
  22. 2024How AI Ideas Affect the Creativity, Diversity, and Evolution of Human Ideas: Evidence From a Large, Dynamic Experimentcited by 22
  23. 2024AgentsCoMerge: Large Language Model Empowered Collaborative Decision Making for Ramp Mergingcited by 22
  24. 2023PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narrativescited by 19
  25. 2024CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Modelscited by 19
  26. 2024A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harmscited by 19
  27. 2024Assistive Large Language Model Agents for Socially-Aware Negotiation Dialoguescited by 18
  28. 2020PolicyKit: Building Governance in Online Communitiescited by 15
  29. 2023Market Concentration Implications of Foundation Modelscited by 15
  30. 2024Stick to your Role! Stability of Personal Values Expressed in Large Language Modelscited by 14
  31. 2023Case Repositories: Towards Case-Based Reasoning for AI Alignmentcited by 11
  32. 2023Toxicity Detection is NOT all you Need: Measuring the Gaps to Supporting Volunteer Content Moderatorscited by 10
  33. 2024Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Normscited by 8
  34. 2022Comparing the Perceived Legitimacy of Content Moderation Processes: Contractors, Algorithms, Expert Panels, and Digital Juriescited by 7
  35. 2024I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Modelscited by 5
  36. 2018Mind Your POV: Convergence of Articles and Editors Towards Wikipedia's Neutrality Normcited by 3
  37. 2023Cura: Curation at Social Media Scalecited by 3
  38. 2020Modular Politics: Toward a Governance Layer for Online Communitiescited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 8.

17 papers.

Sort:

By area:

  1. 2025Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agentscited by 22
  2. 2025Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamicscited by 19
  3. 2025Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferencescited by 6
  4. 2024Large Language Models in Politics and Democracy: A Comprehensive Surveycited by 5
  5. 2025German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studiescited by 4
  6. 2026The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomescited by 3
  7. 2026Multi-Agent Debate Strategies: Survey, Taxonomy, and Challengescited by 3
  8. 2026Agent-Supported Foresight for AI Systemic Risks: AI Agents for Breadth, Experts for Judgmentcited by 2
  9. 2025Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulationcited by 1
  10. 2025Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertisecited by 0
  11. 2025FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocolcited by 0
  12. 2025Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberationcited by 0
5 more
  1. 2026AI and Collective Decisions: Strengthening Legitimacy and Losers' Consentcited by 0
  2. 2026Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectoriescited by 0
  3. 2026Value-Preserving Architectures for Agentic AI Systemscited by 0
  4. 2026From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interactioncited by 0
  5. 2026Small-world Networks of Agents Brainstorm AI Risks to Support Ideationcited by 0