Are Generative Language Models Multicultural? A Study on Hausa Culture and Emotions using ChatGPT
Domaine:
natural language processingType de record:
paper
Créateur:
DudRamChu
DudRamChuHôte:
Large Language Models (LLMs), such as ChatGPT, are widely used to generate content for various purposes and audiences. However, these models may not reflect the cultural and emotional diversity of their users, especially for low-resource languages. In this paper, we investigate how ChatGPT represents Hausa's culture and emotions. We compare responses generated by ChatGPT with those provided by native Hausa speakers on 37 culturally relevant questions. We conducted experiments using emotion analysis and applied two similarity metrics to measure the alignment between human and ChatGPT responses. We also collected human participants ratings and feedback on ChatGPT responses. Our results show that ChatGPT has some level of similarity to human responses, but also exhibits some gaps and biases in its knowledge and awareness of the Hausa culture and emotions. We discuss the implications and limitations of our methodology and analysis and suggest ways to improve the performance and evaluation of LLMs for low-resource languages.
Similaires
Artwork Interpretation with Vision Language Models: A Case Study on Emotions and Emotion SymbolsHow Ready Are Generative Pre-trained Large Language Models for Explaining Bengali Grammatical Errors?Generative phonology and dialect variation: A study of Hausa dialects.Language Models Entangle Language and CultureIn What Languages are Generative Language Models the Most Formal? Analyzing Formality Distribution across LanguagesTalk: How Ready Are Generative Pre-trained Large Language Models for Explaining Bengali Grammatical Errors?