Large language models can replicate cross-cultural differences in personality

📅 2023-10-12
🏛️ Journal of Research in Personality
📈 Citations: 4
Influential: 0
📄 PDF
🤖 AI Summary
This study investigates whether large language models (LLMs) implicitly encode and can reproduce cross-cultural personality differences. Method: Using zero-shot and few-shot prompting with the multilingual Big Five Inventory-2 (BFI-2), we evaluated personality trait outputs of GPT-4, LLaMA, and other LLMs across five cultural groups—including the U.S. and South Korea—and assessed reproducibility via intraclass correlation (ICC) and statistical modeling. Results/Contribution: We provide the first systematic evidence that LLMs significantly replicate nation-level personality differences—particularly in Agreeableness and Conscientiousness—with high fidelity (r = 0.72–0.89), closely aligning with established human cross-cultural findings. Crucially, our analysis demonstrates that LLM training data contain measurable, transferable cultural biases in personality structure, establishing a novel paradigm and empirical benchmark for cultural alignment and bias auditing in LLMs.
Problem

Research questions and friction points this paper is trying to address.

Cultural Differences
Personality Traits
Large Language Models
Innovation

Methods, ideas, or system contributions that make the work stand out.

Large Language Models
Cross-cultural Personality Studies
Cultural Personality Differences
🔎 Similar Papers
No similar papers found.
P
Paweł Niszczota
Humans & AI Laboratory (HAI Lab), Institute of International Business and Economics, Poznań University of Economics and Business, Poznań, Poland
M
Mateusz Janczak
Humans & AI Laboratory (HAI Lab), Institute of International Business and Economics, Poznań University of Economics and Business, Poznań, Poland