@inproceedings{cheng-etal-2026-improving,
    title = "Improving Long-Context Translation via Self-Supervised Dual Learning",
    author = "Cheng, Shanbo  and
      She, Shuaijie  and
      Bao, Yu  and
      Zhang, Jianbing  and
      Chen, Jiajun  and
      Huang, Shujian",
    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.1257/",
    pages = "27269--27280",
    ISBN = "979-8-89176-390-6",
    abstract = "Large language models (LLMs) with long context windows offer the potential to translate entire documents in a single pass, yet they frequently suffer from catastrophic information distortion, undermining the strict faithfulness required for translation. This challenge is compounded by the scarcity of document-level parallel data, which makes both supervised fine-tuning and reliable evaluation prohibitively expensive. We propose LongDu, a self-supervised post-training framework that improves long-document translation reliability via round-trip consistency. Given monolingual documents, LongDu samples multiple candidate translations, back-translates each candidate, and optimizes the model to prefer translations that best reconstruct the source. To make this signal robust for long-form generation, we design a reward that filters trivial failure modes (e.g., copying and local language drift) before applying a reconstruction and fluency score, enabling stable reinforcement learning without human annotations. We additionally introduce Long-CIRT, an automatic evaluation protocol that quantifies information distortion by measuring how much a LLM{'}s performance degrades after a translation cycle. Across multiple base models, LongDu substantially improves information retention and translation quality, with gains that generalize beyond the training length range and to unseen target languages."
}