Large language models can replicate cross-cultural differences in personality
This provides preliminary evidence that large language models can assist cross-cultural researchers and practitioners, though it is incremental as it builds on existing knowledge of personality differences.
The study investigated whether GPT-4 can replicate cross-cultural differences in personality traits between the US and South Korea using the Big Five model, finding that it successfully replicated differences for each factor but with biases such as upward mean ratings and lower variation compared to human samples.
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.