@inproceedings{tan-etal-2026-llm,
    title = "What Does {LLM} Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation",
    author = "Tan, Shaomu  and
      Zhu, Dawei  and
      Tran, Ke  and
      Denkowski, Michael  and
      Trenous, Sony  and
      Ribeiro, Leonardo F. R.  and
      Byrne, Bill  and
      Hieber, Felix",
    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.268/",
    pages = "5929--5957",
    ISBN = "979-8-89176-390-6",
    abstract = "Iterative refinement is a simple inference-time strategy for machine translation: given an initial translation, an LLM revises it without additional training. Yet document-scale refinement remains poorly understood: 1) which pipelines work best, 2) what quality dimensions improve, and 3) how refiners behave. In this paper, we present a systematic study of document-level literary translation, covering six LLMs and seven language pairs. Across nine translation-refinement granularity combinations and five refinement strategies, a) we find a robust recipe: document-level MT followed by segment-level refinement yields the strongest and most stable improvements. In our setting, doc-level refinement often makes fewer edits and leads to smaller or less reliable gains. Surprisingly, a simple general refinement prompt consistently outperforms error-specific prompting and evaluate-then-refine schemes. b) Fine-grained MQM analyses and professional-translator evaluation show that gains come primarily from fluency, with limited improvements in adequacy. c) Probing translator-refiner strength interactions suggests refinement behaves less like targeted post-editing and more like projecting outputs toward the refiner{'}s learned distribution while remaining anchored to the initial translation."
}