@inproceedings{iwakawa-etal-2025-kikis,
    title = "{KIKIS} at {WMT} 2025 General Translation Task",
    author = "Iwakawa, Koichi  and
      Kudo, Keito  and
      Kimura, Subaru  and
      Ito, Takumi  and
      Suzuki, Jun",
    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-1.47/",
    pages = "705--722",
    ISBN = "979-8-89176-341-8",
    abstract = "We participated in the constrained English{--}Japanese track of the WMT 2025 General Machine Translation Task.Our system collected the outputs produced by multiple subsystems, each of which consisted of LLM-based translation and reranking models configured differently (e.g., prompting strategies and context sizes), and reranked those outputs.Each subsystem generated multiple segment-level candidates and iteratively selected the most probable one to construct the document translation.We then reranked the document-level outputs from all subsystems to obtain the final translation.For reranking, we adopted a text-based LLM reranking approach with a reasoning model to take long contexts into account.Additionally, we built a bilingual dictionary on the fly from parallel corpora to make the system more robust to rare words."
}