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

The paper introduces Cultural Divergence Preservation (CDP), a new diagnostic for evaluating whether large language models (LLMs) preserve cross‑country differences when used as synthetic survey respondents. CDP uses a single human calibration to detect cultural flattening (reduced divergence) or caricature (increased divergence) and is shown to vary monotonically with cross‑country divergence, unlike conventional Jensen–Shannon divergence metrics. Experiments across multiple LLM backbones, prompting methods, and survey domains reveal that CDP uncovers systematic discrepancies with traditional fidelity metrics, highlighting that methods favored by those metrics can still produce strong flattening.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms