mlsanityData to 14 Oct 2026

From Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations

arXiv 2610.16498 ↗First posted 12 Oct 2026cs.SI cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Generative Social Simulation (GSS) leverages Large Language Models (LLMs) to create sophisticated personas that define agents with demographics, emotions, and political opinions. While prior work shows that personas compress outputs into stereotypical caricatures, there is no comprehensive study of how these caricatures evolve into collective artifacts when they interact. Using a Twitter-like GSS platform with personas derived from the American National Elections Study (ANES), we ablate three layers of partisan identity: affective polarization markers, party identification, and vote choice, while retaining demographics, ideological positioning and important issues. We find that collective outcomes depend heavily on how survey responses are translated into personas. Removing a few explicitly partisan statements moves the network from near-complete segregation to cross-party ties approaching those of real Twitter networks. We argue that matching one outcome is not evidence for behavioral validity and point to salience as a possible explanation. Surveys ask for a position on every question regardless of its importance to the respondent, and persona construction turns each answer into a direct behavioral instruction. We conclude with a checklist for more comprehensive evaluation of personas in future works.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 54 references that are in the map. First posted on arXiv 12 Oct 2026.

Builds on

30 of 54 references.

References · 30

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  3. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  4. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 233
  5. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 207
  6. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 206
  7. 2024Large language models that replace human participants can harmfully misportray and flatten identity groupscited by 144
  8. 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 132
  9. 2023CoMPosT: Characterizing and Evaluating Caricature in LLM Simulationscited by 97
  10. 2024PersonaGym: Evaluating Persona Agents and LLMscited by 97
  11. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 82
  12. 2025LLM Generated Persona is a Promise with a Catchcited by 81
18 more
  1. 2024Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulationcited by 71
  2. 2023Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithmscited by 65
  3. 2024Y Social: an LLM-powered Social Media Digital Twincited by 44
  4. 2024LLMs generate structurally realistic social networks but overestimate political homophilycited by 33
  5. 2024Network Formation and Dynamics Among Multi-LLMscited by 29
  6. 2024Agent-Based Modelling Meets Generative AI in Social Network Simulationscited by 26
  7. 2025GA-S3: Comprehensive Social Network Simulation with Group Agentscited by 19
  8. 2025Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoningcited by 13
  9. 2025LLM-Based Social Simulations Require a Boundarycited by 12
  10. 2025Can Generative Agent-Based Modeling Replicate the Friendship Paradox in Social Media Simulations?cited by 10
  11. 2025Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicitycited by 9
  12. 2026Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Auditscited by 8
  13. 2026Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondentscited by 8
  14. 2025Large Language Model Driven Agents for Simulating Echo Chamber Formationcited by 7
  15. 2025Computational Turing Test Reveals Systematic Differences Between Human and AI Languagecited by 6
  16. 2025Can We Fix Social Media? Testing Prosocial Interventions using Generative Social Simulationcited by 4
  17. 2025Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypescited by 3
  18. 2025Don't Think of the White Bear: Ironic Negation in Transformer Models Under Cognitive Loadcited by 2

Built on by

Not cited yet.