@inproceedings{menis-mastromichalakis-etal-2025-assumed,
    title = "Assumed Identities: Quantifying Gender Bias in Machine Translation of Gender-Ambiguous Occupational Terms",
    author = "Menis Mastromichalakis, Orfeas  and
      Filandrianos, Giorgos  and
      Symeonaki, Maria  and
      Stamou, Giorgos",
    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.1640/",
    pages = "32221--32237",
    ISBN = "979-8-89176-332-6",
    abstract = "Machine Translation (MT) systems frequently encounter gender-ambiguous occupational terms, where they must assign gender without explicit contextual cues. While individual translations in such cases may not be inherently biased, systematic patterns{---}such as consistently translating certain professions with specific genders{---}can emerge, reflecting and perpetuating societal stereotypes. This ambiguity challenges traditional instance-level single-answer evaluation approaches, as no single gold standard translation exists. To address this, we introduce GRAPE, a probability-based metric designed to evaluate gender bias by analyzing aggregated model responses. Alongside this, we present GAMBIT, a benchmarking dataset in English with gender-ambiguous occupational terms. Using GRAPE, we evaluate several MT systems and examine whether their gendered translations in Greek and French align with or diverge from societal stereotypes, real-world occupational gender distributions, and normative standards."
}