Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models

arXiv:2310.12481v2 Announce Type: replace
Abstract: This paper identifies a cultural dominance issue within large language models (LLMs) due to the predominant use of English data in model training (e.g., ChatGPT). LLMs often provide inappropriate English-culture-related answers that are not relevant to the expected culture when users ask in non-English languages. To systematically evaluate the cultural dominance issue, we build a benchmark of concrete (e.g., holidays and songs) and abstract (e.g., values and opinions) cultural objects. Empirical results show that the …

abstract arxiv chatgpt cs.ai cs.cl culture data english issue language language models large language large language models llms paper thanksgiving training type