@inproceedings{grubisic-korencic-2025-irb-mt,
    title = "{IRB}-{MT} at {WMT}25 Terminology Translation Task: Metric-guided Multi-agent Approach",
    author = "Grubi{\v{s}}i{\'c}, Ivan  and
      Korencic, Damir",
    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-1.110/",
    pages = "1302--1334",
    ISBN = "979-8-89176-341-8",
    abstract = "Terminology-aware machine translation (MT) is needed in case of specialized domains such as science and law. Large Language Models (LLMs) have raised the level of state-of-art performance on the task of MT, but the problem is not completely solved, especially for use-cases requiring precise terminology translations. We participate in the WMT25 Terminology Translation Task with an LLM-based multi-agent system coupled with a custom terminology-aware translation quality metric for the selection of the final translation. We use a number of smaller open-weights LLMs embedded in an agentic ``translation revision'' workflow, and we do not rely on data- and compute-intensive fine-tuning of models. Our evaluations show that the system achieves very good results in terms of both MetricX-24 and a custom TSR metric designed to measure the adherence to predefined term mappings."
}