Résultats du processus de synthèse de l'article arXiv : 2309.12342v1

Résumé : The deployment of large language models (LLMs) raises concerns regarding their cultural misalignment and potential ramifications on individuals from various cultural norms. Existing work investigated political and social biases and public opinions rather than their cultural values. To address this limitation, the proposed Cultural Alignment Test (CAT) quantifies cultural alignment using Hofstede's cultural dimension framework, which offers an explanatory cross-cultural comparison through the latent variable analysis. We apply our approach to assess the cultural values embedded in state-of-the-art LLMs, such as: ChatGPT and Bard, across diverse cultures of countries: United States (US), Saudi Arabia, China, and Slovakia, using different prompting styles and hyperparameter settings. Our results not only quantify cultural alignment of LLMs with certain countries, but also reveal the difference between LLMs in explanatory cultural dimensions. While all LLMs did not provide satisfactory results in understanding cultural values, GPT-4 exhibited the highest CAT score for the cultural values of the US.