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

arXiv: https://arxiv.org/abs/2610.16498 · HTML: https://mlsanity.com/paper/2610.16498/

## 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 (most cited first, 30 of 30)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [Large language models that replace human participants can harmfully misportray and flatten identity groups](https://mlsanity.com/paper/2402.01908/) (2024)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations](https://mlsanity.com/paper/2310.11501/) (2023)
- [PersonaGym: Evaluating Persona Agents and LLMs](https://mlsanity.com/paper/2407.18416/) (2024)
- [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024)
- [LLM Generated Persona is a Promise with a Catch](https://mlsanity.com/paper/2503.16527/) (2025)
- [Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulation](https://mlsanity.com/paper/2402.16333/) (2024)
- [Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms](https://mlsanity.com/paper/2310.05984/) (2023)
- [Y Social: an LLM-powered Social Media Digital Twin](https://mlsanity.com/paper/2408.00818/) (2024)
- [LLMs generate structurally realistic social networks but overestimate political homophily](https://mlsanity.com/paper/2408.16629/) (2024)
- [Network Formation and Dynamics Among Multi-LLMs](https://mlsanity.com/paper/2402.10659/) (2024)
- [Agent-Based Modelling Meets Generative AI in Social Network Simulations](https://mlsanity.com/paper/2411.16031/) (2024)
- [GA-S3: Comprehensive Social Network Simulation with Group Agents](https://mlsanity.com/paper/2506.03532/) (2025)
- [Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning](https://mlsanity.com/paper/2506.20020/) (2025)
- [LLM-Based Social Simulations Require a Boundary](https://mlsanity.com/paper/2506.19806/) (2025)
- [Can Generative Agent-Based Modeling Replicate the Friendship Paradox in Social Media Simulations?](https://mlsanity.com/paper/2502.05919/) (2025)
- [Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity](https://mlsanity.com/paper/2507.00657/) (2025)
- [Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits](https://mlsanity.com/paper/2605.18890/) (2026)
- [Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents](https://mlsanity.com/paper/2608.14606/) (2026)
- [Large Language Model Driven Agents for Simulating Echo Chamber Formation](https://mlsanity.com/paper/2502.18138/) (2025)
- [Computational Turing Test Reveals Systematic Differences Between Human and AI Language](https://mlsanity.com/paper/2511.04195/) (2025)
- [Can We Fix Social Media? Testing Prosocial Interventions using Generative Social Simulation](https://mlsanity.com/paper/2508.03385/) (2025)
- [Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes](https://mlsanity.com/paper/2501.14294/) (2025)
- [Don't Think of the White Bear: Ironic Negation in Transformer Models Under Cognitive Load](https://mlsanity.com/paper/2511.12381/) (2025)

## 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.