Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledge

arXiv:2404.06833v1 Announce Type: new
Abstract: Recent studies have highlighted the presence of cultural biases in Large Language Models (LLMs), yet often lack a robust methodology to dissect these phenomena comprehensively. Our work aims to bridge this gap by delving into the Food domain, a universally relevant yet culturally diverse aspect of human life. We introduce FmLAMA, a multilingual dataset centered on food-related cultural facts and variations in food practices. We analyze LLMs across various architectures and configurations, evaluating their performance …

abstract arxiv biases bridge coffee cs.cl diverse domain food gap knowledge language language models large language large language models llms methodology robust studies type work