Article

Large language models capture universal relationship knowledge but compress cultural variation

2026-06-14

Abstract excerpt

<p>Can large language models (LLMs) represent how people understand relationships across cultures? We tested four prominent LLMs against human benchmark data from more than 20,000 participants across 19 global regions using the FAVEE framework, which represents 159 interpersonal relationships along 33 relational features. LLMs closely matched human ratings at the aggregate level and reproduced the broad multidimen...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 52c04600-85db-5914-a525-6a5b8a2ac6a4
DOI: 10.31234/osf.io/35tmz_v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Large language models capture universal relationship knowledge but compress cultural variationDOI 10.31234/osf.io/35tmz_v1Read

A Multi-Factor Evaluation of Fidelity in LLM-Based Cross-Cultural SurrogatesSemantic proximity Read

Local similarity and global variability characterize the semantic space of human languagesSemantic proximity Read

Which Humans?Semantic proximity Read

Evaluating Large Language Models in Psychological Research: A Guide for ReviewersSemantic proximity Read

Individual uniqueness in trust profiles and well-being: Understanding the role of cultural tightness-looseness from a representation similarity perspectiveSemantic proximity Read

A Causal Framework for Cross-Cultural GeneralizabilitySemantic proximity Read

Multimodal large language models encode implicit gender biasSemantic proximity Read

Exploring Universal Human Values with Large Language Models: The AWARE-Value ModelSemantic proximity Read

Large language models as linguistic simulators and cognitive models in human researchSemantic proximity Read

Utilizing AI questionnaire translations in cross-cultural and intercultural research: Insights and recommendationsSemantic proximity Read

Perils and Opportunities in Using Large Language Models in Psychological ResearchSemantic proximity Read

Language enables cumulative cultural improvement by transmitting mental modelsSemantic proximity Read