CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting

arXiv:2404.10199v1 Announce Type: new
Abstract: As the utilization of large language models (LLMs) has proliferated worldwide, it is crucial for them to have adequate knowledge and fair representation for diverse global cultures. In this work, we uncover culture perceptions of three SOTA models on 110 countries and regions on 8 culture-related topics through culture-conditioned generations, and extract symbols from these generations that are associated to each culture by the LLM. We discover that culture-conditioned generation consist of linguistic "markers" that …

arxiv cs.ai cs.cl culture gen global language language models natural natural language perception prompting through type