@InProceedings{matsuda-EtAl:2026:wmt,
  author    = {Matsuda, Ryosuke  and  Kudo, Keito  and  Fujii, Ryo  and  Ito, Takumi  and  Morishita, Makoto  and  Suzuki, Jun},
  title     = {RFMT at WMT 2026 General Translation Task},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {1351--1378},
  abstract  = {We participated in the constrained (open-weight) track of the WMT 2026 General MT Task for the English-to-Japanese and Simplified Chinese-to-Japanese directions. Our system builds on Marco-MT-Algharb, a strong open-weight translation model from the previous WMT General MT task. We further fine-tuned this model to generate more natural Japanese translations. To this end, we constructed a Context-Aware JApanese Linguistic Acceptability dataset (CAJALA). During annotation, human annotators were shown multiple paraphrased variants of a segment within its document-level context and asked to select the most natural one. We then back-translated the CAJALA dataset to create parallel data for Direct Preference Optimization (DPO). We also trained the model to perform fill-in-the-middle (FIM) translation, in which the model reconstructs target-side segments from their surrounding document. At inference, we use Minimum Bayes Risk (MBR) decoding, followed by selective FIM post-editing of low-quality segments.},
  url       = {https://aclanthology.org/2026.wmt-1.73}
}