LLMs have limitations when it comes to cultural coverage and competence, and in some cases, show specific cultural biases. Although prior studies have examined the cultural capabilities of LLMs, none have specifically investigated their regional preferences in generic culture-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ), with questions available in 24 languages. We evaluate LLMs by prompting them to answer questions from CROQ and provide a sample location. The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan in their answers. Moreover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs. Low-resource languages, on the other hand, show more inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training. Dataset available at https://huggingface.co/datasets/HiTZ/CROQ
A dataset with substantial coverage of non-WEIRD cultures and five-dimensional annotations supports an interpretable approach to examining weaknesses in LLMs’ cross-cultural alignment and suggests that WEIRD data bias reflects both the underrepresentation of low-WEIRD cultures and the overactivation of dominant value f...
Meng-Xi Guo, Lei-Ming Gao, W. Zeng et al.· Big Data and Cognitive Compu...· 0 citations
As Large Language Models (LLMs) are increasingly integrated into human society, aligning them with pluralistic social values has become a critical priority. However, whether LLMs exhibit consistent value preferences across languages remains underexplored, particularly for culturally grounded values, which are more abst...
Yue-Mei Xu, Ke-Xin Xu, Jian Zhou et al.· 0 citations
The notable findings suggest that LLMs often make basic errors of grammar and semantics, and highlight the limitations of current LLMs as a reliable source of content generation and information retrieval for low-resource languages.
Farah Adeeba, A. Khan, Rajesh Bhatt et al.· 0 citations
Cultural evaluation of large language models (LLMs) often focuses on high-resource standard languages, leaving regional culture and dialect communities underrepresented. We introduce BavGround, a benchmark for evaluating Bavarian regional cultural grounding and dialect competence across English, German and Bavarian. Ba...
Jophin John, Michael Hoffmann, Jan Fillies et al.· 0 citations
As Large Language Models (LLMs) continue to scale both in size and capabilities, their proficiency in the Arabic Language has seen significant advancement. However, a critical gap remains: the extent of their factual knowledge and cultural sensitivity to the diverse Arabic-speaking world remains largely underexplored....
Ignacio Iacobacci, Faroq Al-Tam, Zhao-Zhi Qian et al.· 0 citations
Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more commonly used by women (hedges, tag questions, collective reference), they systematically elicit shorter, less sophisticated, and less formal responses ac...