People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe

2026-08-07

AI Summary

This study addresses a critical gap in prior research, which often defines populations solely by national or cultural boundaries while overlooking the influence of sociodemographic factors on value alignment in large language models (LLMs). Leveraging European Social Survey data, this work systematically disentangles the independent and interactive effects of national affiliation and 15 sociodemographic variables—including education, income, occupation, and religiosity—on value alignment across 10 mainstream commercial LLMs. Through large-scale survey analysis, multivariate regression, and variance decomposition, the study reveals significant inequities in how LLMs align with the values of different social groups. Notably, national identity alone accounts for a comparable share of alignment variation as the combined set of sociodemographic variables, underscoring their complementary roles and context-dependent relative importance across different value-laden topics.

Abstract

As Large Language Models (LLMs) are increasingly used as a primary source of information and advice, understanding their alignment to humans in terms of values becomes a pressing concern. A growing literature has leveraged large scale surveys to investigate to what extent LLMs' and humans' stated values and opinions align. With limited exceptions, studied populations have been defined country borders or cultural bounds. Yet, this focus neglects the role that socio-demographic divides may play for value alignment disparities. Relying on the European Social Survey, we address this knowledge gap by considering value alignment displayed with respect to 10 prominent commercial LLMs in terms of 15 socio-demographic variables as well as country of residence. Our analyses reveal that LLMs are indeed unequally aligned to the values of different socio-demographic groups, notably those defined by education, income, occupation and religion. When examining alignment at the individual level, a respondent's country, taken as a stand-alone variable, explains a substantial amount of variation that is on par with the full set of considered socio-demographics. Further disentangling the respective role of country-level and socio-demographic factors, we find they are complementary in explaining value alignment patterns, with their relative weights varying across the subset of questions considered.

Problem

• value alignment
• socio-demographic factors
• Large Language Models
• European Social Survey
• cross-national variation

Innovation

• value alignment
• socio-demographic factors
• large language models
• European Social Survey
• disentanglement