@inproceedings{verma-etal-2026-safari,
    title = "{SAFARI}: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-{S}aharan {A}frican Context",
    author = "Verma, Aishwarya  and
      Ammah, Laud  and
      Lucas, Olivia Nercy Ndlovu  and
      Zaldivar, Andrew  and
      Prabhakaran, Vinodkumar  and
      Dev, Sunipa",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-short.27/",
    pages = "359--370",
    ISBN = "979-8-89176-381-4",
    abstract = "Stereotype repositories are critical to assess generative AI model safety, but currently lack adequate global coverage. It is imperative to prioritize targeted expansion, strategically addressing existing deficits, over merely increasing data volume. This work introduces a multilingual stereotype resource covering four sub-Saharan African countries that are severely underrepresented in NLP resources: Ghana, Kenya, Nigeria, and South Africa. By utilizing socioculturally-situated, community-engaged methods, including telephonic surveys moderated in native languages, we establish a reproducible methodology that is sensitive to the region{'}s complex linguistic diversity and traditional orality. By deliberately balancing the sample across diverse ethnic and demographic backgrounds, we ensure broad coverage, resulting in a dataset of 3,534 stereotypes in English and 3,206 stereotypes across 15 native languages."
}