@inproceedings{luo-etal-2026-niutrans,
    title = "{N}iu{T}rans.{LMT}: Toward Inclusive and Scalable Multilingual Machine Translation with {LLM}s",
    author = "Luo, Yingfeng  and
      Xu, Ziqiang  and
      Ouyang, Yuxuan  and
      Yang, MuRun  and
      Lin, DingYang  and
      Chang, Kaiyan  and
      Zheng, Tong  and
      Li, Bei  and
      Feng, Peinan  and
      Du, Quan  and
      Xiao, Tong  and
      Zhu, JingBo",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1153/",
    pages = "25151--25179",
    ISBN = "979-8-89176-390-6",
    abstract = "Large language models have significantly advanced Multilingual Machine Translation (MMT), yet scaling to many languages while keeping quality robust across directions remains challenging.In this paper, we identify a failure mode of multilingual supervised fine-tuning (SFT) on multi-way parallel data: when such data are reused symmetrically around a pivot language (e.g., English), performance on reverse directions (X $\to$ pivot) can drop substantially.We term this phenomenon Directional Degeneration and attribute it to excessive many-to-one mappings, which encourage shortcut learning.We propose Strategic Downsampling (SD), a simple yet effective method to mitigate this degeneration.In addition, we introduce Parallel Multilingual Prompting (PMP), which augments translation instructions with an auxiliary parallel sentence to promote cross-lingual transfer during training and enables optional test-time enhancement when auxiliary translations are available. We further develop \textbf{NiuTrans.LMT} (\textbf{L}arge-scale \textbf{M}ultilingual \textbf{T}ranslation, abbreviated as \textbf{LMT}), a Chinese{--}English-centric suite of multilingual translation models spanning four sizes (0.6B/1.7B/4B/8B) and covering 60 languages and 234 directions.Comprehensive evaluations show that LMT is competitive among open-source MMT systems, and that our 4B LMT model performs on par with or better than substantially larger baselines. We release our models and project resources to support inclusive and scalable MMT."
}