@inproceedings{guo-etal-2025-care,
    title = "{CARE}: Multilingual Human Preference Learning for Cultural Awareness",
    author = "Guo, Geyang  and
      Naous, Tarek  and
      Wakaki, Hiromi  and
      Nishimura, Yukiko  and
      Mitsufuji, Yuki  and
      Ritter, Alan  and
      Xu, Wei",
    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.1669/",
    pages = "32854--32883",
    ISBN = "979-8-89176-332-6",
    abstract = "Language Models (LMs) are typically tuned with human preferences to produce helpful responses, but the impact of preference tuning on the ability to handle culturally diverse queries remains understudied. In this paper, we systematically analyze how native human cultural preferences can be incorporated into the preference learning process to train more culturally aware LMs. We introduce \textbf{CARE}, a multilingual resource containing 3,490 culturally specific questions and 31.7k responses with human judgments. We demonstrate how a modest amount of high-quality native preferences improves cultural awareness across various LMs, outperforming larger generic preference data. Our analyses reveal that models with stronger initial cultural performance benefit more from alignment, leading to gaps among models developed in different regions with varying access to culturally relevant data. CARE is publicly available at \url{https://github.com/Guochry/CARE}."
}