@inproceedings{dai-etal-2025-word,
    title = "From Word to World: Evaluate and Mitigate Culture Bias in {LLM}s via Word Association Test",
    author = "Dai, Xunlian  and
      Zhou, Li  and
      Wang, Benyou  and
      Li, Haizhou",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1246/",
    pages = "24521--24537",
    ISBN = "979-8-89176-332-6",
    abstract = "The human-centered word association test (WAT) serves as a cognitive proxy, revealing sociocultural variations through culturally shared semantic expectations and implicit linguistic patterns shaped by lived experiences. We extend this test into an LLM-adaptive, free-relation task to assess the alignment of large language models (LLMs) with cross-cultural cognition. To address culture preference, we propose \textit{CultureSteer}, an innovative approach that moves beyond superficial cultural prompting by embedding cultural-specific semantic associations directly within the model{'}s internal representation space. Experiments show that current LLMs exhibit significant bias toward Western (notably American) schemas at the word association level. In contrast, our model substantially improves cross-cultural alignment, capturing diverse semantic associations. Further validation on culture-sensitive downstream tasks confirms its efficacy in fostering cognitive alignment across cultures. This work contributes a novel methodological paradigm for enhancing cultural awareness in LLMs, advancing the development of more inclusive language technologies."
}