Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populations

arXiv:2609.29928 · cs.CL, cs.AI · Submitted 2026-09-24 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-24

Updated: 2026-09-24

Terminology

• Fidelity — 22× in this paper · explained in 2 episodes
• Cultural Divergence — 10× in this paper
• Cultural Divergence Preservation — 7× in this paper
• Alignment — 4× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Core — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Wasserstein Distance — 2× in this paper · explained in 4 episodes
• Distribution Matching — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes

Sources

• PLURAL: A Global Dataset for Value Alignment
• Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency
• Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data
• Polypersona: Persona-Grounded LLM for Synthetic Survey Responses
• Towards Measuring the Representation of Subjective Global Opinions in Language Models
• Scaling Synthetic Data Creation with 1,000,000,000 Personas
• Gemma 3 Technical Report
• This human study did not involve human subjects: Validating LLM simulations as behavioral evidence
• The American Ghost in the Machine: How language models align culturally and the effects of cultural prompting
• Assessing the Reliability of Persona-Conditioned LLMs as Synthetic Survey Respondents
• Qwen3.5-Omni Technical Report
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas
• DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas
• A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering