@inproceedings{uhlig-etal-2025-cross,
    title = "Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization",
    author = "Uhlig, Kaden  and
      Wuebker, Joern  and
      Reinauer, Raphael  and
      Denero, John",
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Tenth Conference on Machine Translation",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.wmt-1.2/",
    pages = "31--51",
    ISBN = "979-8-89176-341-8",
    abstract = "Reinforcement Learning from Human Feedback (RLHF) and derivative techniques like Direct Preference Optimization (DPO) are task-alignment algorithms used to repurpose general, foundational models for specific tasks. We show that applying task-alignment to neural machine translation (NMT) addresses an existing task{--}data mismatch in NMT, leading to improvements across all languages of a multilingual model, even when task-alignment is only applied to a subset of those languages. We do so by introducing Direct Quality Optimization (DQO), a variant of DPO leveraging a pre-trained translation quality estimation model as a proxy for human preferences, and verify the improvements with both automatic metrics and through human evaluation."
}