@inproceedings{taguchi-etal-2025-languages,
    title = "Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark",
    author = "Taguchi, Chihiro  and
      Mai, Seng  and
      Kurabe, Keita  and
      Sakai, Yusuke  and
      Agyei, Georgina  and
      Eslami, Soudabeh  and
      Chiang, David",
    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.1018/",
    pages = "20142--20154",
    ISBN = "979-8-89176-332-6",
    abstract = "Multilingual machine translation (MT) benchmarks play a central role in evaluating the capabilities of modern MT systems. Among them, the FLORES+ benchmark is widely used, offering English-to-many translation data for over 200 languages, curated with strict quality control protocols. However, we study data in four languages (Asante Twi, Japanese, Jinghpaw, and South Azerbaijani) and uncover critical shortcomings in the benchmark{'}s suitability for truly multilingual evaluation. Human assessments reveal that many translations fall below the claimed 90{\%} quality standard, and the annotators report that source sentences are often too domain-specific and culturally biased toward the English-speaking world. We further demonstrate that simple heuristics, such as copying named entities, can yield non-trivial BLEU scores, suggesting vulnerabilities in the evaluation protocol. Notably, we show that MT models trained on naturalistic data perform poorly on FLORES+ while achieving significant gains on our domain-relevant evaluation set. Based on these findings, we advocate for multilingual MT benchmarks that use domain-general, named-entity-agnostic, and culturally neutral source texts to better reflect real-world translation challenges."
}