Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks

TL;DR

This paper explores how large language models can generate culturally-grounded personas that reflect real-world and moral values across different cultures, using established socio-psychological frameworks for evaluation.

Contribution

It introduces a method to generate and analyze LLM personas aligned with cultural and moral frameworks, enabling better cross-cultural understanding and model alignment.

Findings

Generated personas align with cultural maps and value surveys.

Response patterns reflect demographic and cultural differences.

Moral profiles vary systematically across cultural configurations.

Abstract

Despite the growing utility of Large Language Models (LLMs) for simulating human behavior, the extent to which these synthetic personas accurately reflect world and moral value systems across different cultural conditionings remains uncertain. This paper investigates the alignment of synthetic, culturally-grounded personas with established frameworks, specifically the World Values Survey (WVS), the Inglehart-Welzel Cultural Map, and Moral Foundations Theory. We conceptualize and produce LLM-generated personas based on a set of interpretable WVS-derived variables, and we examine the generated personas through three complementary lenses: positioning on the Inglehart-Welzel map, which unveils their interpretation reflecting stable differences across cultural conditionings; demographic-level consistency with the World Values Survey, where response distributions broadly track human group patterns; and moral profiles derived from a Moral Foundations questionnaire, which we analyze through a culture-to-morality mapping to characterize how moral responses vary across different cultural configurations. Our approach of culturally-grounded persona generation and analysis enables evaluation of cross-cultural structure and moral variation.