@inproceedings{feng-etal-2025-tear,
    title = "{TE}a{R}: Improving {LLM}-based Machine Translation with Systematic Self-Refinement",
    author = "Feng, Zhaopeng  and
      Zhang, Yan  and
      Li, Hao  and
      Wu, Bei  and
      Liao, Jiayu  and
      Liu, Wenqiang  and
      Lang, Jun  and
      Feng, Yang  and
      Wu, Jian  and
      Liu, Zuozhu",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-naacl.218/",
    pages = "3922--3938",
    ISBN = "979-8-89176-195-7",
    abstract = "Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). However, human evaluations reveal that LLM-generated translations still contain various errors. Notably, feeding the error information back into the LLMs can facilitate self-refinement, leading to enhanced translation quality. Motivated by these findings, we introduce TEaR (Translate, Estimate, and Refine), a systematic LLM-based self-refinement framework aimed at bootstrapping translation performance. Our key results show that: 1) TEaR framework enables LLMs to improve their translation quality relying solely on self-feedback, measured by both automatic metrics and Multidimensional Quality Metrics (MQM) scores; 2) TEaR autonomously selects improvements, ensuring a robust translation quality baseline while outperforming both internal refinement and external feedback methods. Error analysis and iterative refinement experiments show its ability to continuously reduce translation errors and enhance overall translation quality. Our code and data are publicly available at https://github.com/fzp0424/self{\_}correct{\_}mt."
}