@inproceedings{bui-etal-2025-multi3hate,
    title = "{M}ulti$^3${H}ate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision{--}Language Models",
    author = "Bui, Minh Duc  and
      Wense, Katharina Von Der  and
      Lauscher, Anne",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.naacl-long.490/",
    pages = "9714--9731",
    ISBN = "979-8-89176-189-6",
    abstract = "Hate speech moderation on global platforms poses unique challenges due to the multimodal and multilingual nature of content, along with the varying cultural perceptions. How well do current vision-language models (VLMs) navigate these nuances? To investigate this, we create the first multimodal and multilingual parallel hate speech dataset, annotated by a multiculturally diverse set of annotators, called Multi$^3$Hate. It contains 300 parallel meme samples across 5 languages: English, German, Spanish, Hindi, and Mandarin. We demonstrate that cultural background significantly affects multimodal hate speech annotation in our dataset. The average pairwise agreement among countries is just 74{\%}, significantly lower than that of randomly selected annotator groups. Our qualitative analysis indicates that the lowest pairwise label agreement{---}only 67{\%} between the USA and India{---}can be attributed to cultural factors. We then conduct experiments with 5 large VLMs in a zero-shot setting, finding that these models align more closely with annotations from the US than with those from other cultures, even when the memes and prompts are presented in the native language of the other culture."
}