Large language models can replicate cross-cultural differences in personality

What the paper says

• We assess whether GPT-4 can replicate cross-cultural differences in personality. • We focus on the Big Five , measured using the Ten-Item Personality Inventory. • GPT-4 replicated differences between US Americans and South Koreans for all factors. • However, scores had an upward bias, lower variation, and lower structural validity. • Nonetheless, large language models have the potential to aid cross-cultural studies. We use a large-scale experiment ( N = 8000) to determine whether GPT-4 can replicate cross-cultural differences in the Big Five, measured using the Ten-Item Personality Inventory. We used the US and South Korea as the cultural pair, given that prior research suggests substantial personality differences between people from these two countries. We manipulated the target of the simulation (US vs. Korean), the language of the inventory (English vs. Korean), and the language model (GPT-4 vs. GPT-3.5). Our results show that GPT-4 replicated the cross-cultural differences for each factor. However, mean ratings had an upward bias and exhibited lower variation than in the human samples, as well as lower structural validity. We provide preliminary evidence that LLMs can aid cross-cultural researchers and practitioners.