@inproceedings{tan-etal-2025-towards,
    title = "Towards Massive Multilingual Holistic Bias",
    author = "Tan, Xiaoqing  and
      Hansanti, Prangthip  and
      Turkatenko, Arina  and
      Chuang, Joe  and
      Wood, Carleigh  and
      Yu, Bokai  and
      Ropers, Christophe  and
      Costa-juss{\`a}, Marta R.",
    editor = "Fale{\'n}ska, Agnieszka  and
      Basta, Christine  and
      Costa-juss{\`a}, Marta  and
      Sta{\'n}czak, Karolina  and
      Nozza, Debora",
    booktitle = "Proceedings of the 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.gebnlp-1.35/",
    pages = "403--426",
    ISBN = "979-8-89176-277-0",
    abstract = "In the current landscape of automatic language generation, there is a need to understand, evaluate, and mitigate demographic biases, as existing models are becoming increasingly multilingual. To address this, we present the initial eight languages from the Massive Multilingual Holistic Bias (MMHB) dataset and benchmark consisting of approximately 6 million sentences. The sentences are designed to induce biases towards different groups of people which can yield significant results when using them as a benchmark to test different text generation models. To further scale up in terms of both language coverage and size and to leverage limited human translation, we use systematic approach to independently translate sentence parts. This technique carefully designs a structure to dynamically generate multiple sentence variations and significantly reduces the human translation workload. The translation process has been meticulously conducted to avoid an English-centric perspective and include all necessary morphological variations for languages that require them, improving from the original English HOLISTICBIAS. Finally, we utilize MMHB to report results on gender bias and added toxicity in MT tasks."
}