mlsanityData to 7 Oct 2026

The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents

arXiv 2311.09665 ↗First posted 16 Nov 2023cs.CLcited by 30

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Human groups are able to converge on more accurate beliefs through deliberation, even in the presence of polarization and partisan bias -- a phenomenon known as the "wisdom of partisan crowds." Generated agents powered by Large Language Models (LLMs) are increasingly used to simulate human collective behavior, yet few benchmarks exist for evaluating their dynamics against the behavior of human groups. In this paper, we examine the extent to which the wisdom of partisan crowds emerges in groups of LLM-based agents that are prompted to role-play as partisan personas (e.g., Democrat or Republican). We find that they not only display human-like partisan biases, but also converge to more accurate beliefs through deliberation as humans do. We then identify several factors that interfere with convergence, including the use of chain-of-thought prompt and lack of details in personas. Conversely, fine-tuning on human data appears to enhance convergence. These findings show the potential and limitations of LLM-based agents as a model of human collective intelligence.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 11 of its 29 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

11 of 29 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 10

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2022Emergent Abilities of Large Language Modelscited by 2,483
  4. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 300
  5. 2022On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoningcited by 191
  6. 2023Turning large language models into cognitive modelscited by 66
  7. 2023Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithmscited by 64
  8. 2023Lyfe Agents: Generative agents for low-cost real-time social interactionscited by 49
  9. 2023Quantifying the Impact of Large Language Models on Collective Opinion Dynamicscited by 22
  10. 2023Computational Agent-based Models in Opinion Dynamics: A Survey on Social Simulations and Empirical Studiescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 15; 2026: 7.

30 papers.

Sort:

By area:

  1. 2025LLM Generated Persona is a Promise with a Catchcited by 77
  2. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 76
  3. 2024LLM Voting: Human Choices and AI Collective Decision Makingcited by 47
  4. 2024Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networkscited by 39
  5. 2024AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarioscited by 37
  6. 2025Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulationscited by 28
  7. 2024LLM-based multi-agent poetry generation in non-cooperative environmentscited by 15
  8. 2024A Survey on Human-Centric LLMscited by 13
  9. 2026Does Socialization Emerge in AI Agent Society? A Case Study of Moltbookcited by 13
  10. 2025Bridging the Creativity Understanding Gap: Small-Scale Human Alignment Enables Expert-Level Humor Ranking in LLMscited by 12
  11. 2025BookWorld: From Novels to Interactive Agent Societies for Creative Story Generationcited by 12
  12. 2025The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societiescited by 12
18 more
  1. 2026PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimizationcited by 10
  2. 2025Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowdscited by 6
  3. 2026Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Auditscited by 6
  4. 2024Large Language Models can Achieve Social Balancecited by 5
  5. 2025AI Agent Behavioral Sciencecited by 5
  6. 2025To Mask or to Mirror: Human-AI Alignment in Collective Reasoningcited by 5
  7. 2025DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agentscited by 5
  8. 2025The Society of HiveMind: Multi-Agent Optimization of Foundation Model Swarms to Unlock the Potential of Collective Intelligencecited by 4
  9. 2025Finding Common Ground: Using Large Language Models to Detect Agreement in Multi-Agent Decision Conferencescited by 3
  10. 2026AI Agents Alone Are Not (Yet) Sufficient for Social Simulationcited by 3
  11. 2024Neuro-Symbolic Traders: Assessing the Wisdom of AI Crowds in Marketscited by 2
  12. 2025Bridging Minds and Machines: Toward an Integration of AI and Cognitive Sciencecited by 2
  13. 2025Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Modelscited by 2
  14. 2025Collaborative QA using Interacting LLMs. Impact of Network Structure, Node Capability and Distributed Datacited by 2
  15. 2026An Empirical Study of Collective Behaviors and Social Dynamics in Large Language Model Agentscited by 2
  16. 2026From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communitiescited by 2
  17. 2025Bypassing Safety Guardrails in LLMs Using Humorcited by 1
  18. 2026CogEvolution: A Human-like Generative Educational Agent to Simulate Student's Cognitive Evolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Systematic Biases in LLM Simulations of Debates
  2. 2025An Empirical Study of Group Conformity in Multi-Agent Systems
  3. 2026Toward a social psychology of AI: language-model agents reproduce human-like minimal-group bias
  4. 2026Multi-Agent Consensus as a Cognitive Bias Trigger in Human-AI Interaction
  5. 2025Emergence of polarization in networks of large language model agents
  6. 2023Simulating Opinion Dynamics with Networks of LLM-based Agents
  7. 2025Revealing Political Bias in LLMs through Structured Multi-Agent Debate
  8. 2024GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy