@inproceedings{yoshida-etal-2026-tablembr,
    title = "{T}able{MBR}: Minimum {B}ayes Risk Table Generation Based on Structural Consistency",
    author = "Yoshida, Daiki  and
      Deguchi, Hiroyuki  and
      Sakai, Yusuke  and
      Kamigaito, Hidetaka  and
      Watanabe, Taro",
    editor = "T.Y.S.S., Santosh  and
      Rodriguez, Juan Diego  and
      de Gibert, Ona",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-srw.95/",
    pages = "1087--1102",
    ISBN = "979-8-89176-393-7",
    abstract = "The text-to-table task aims to generate structured data in tabular formats from unstructured text. While the integration of large language models (LLMs) has significantly enhanced the comprehensiveness and flexibility of generation, challenges regarding inconsistent output quality persist, such as the inclusion of redundant information and numerical inaccuracies. We propose TableMBR, a robust table generation method that maintains structural consistency through minimum Bayes risk (MBR) decoding. Experimental results showed that TableMBR outperforms the baseline, achieving relative improvements of up to 15{\%} in F1 score on Rotowire and 23{\%} in accuracy on LiveSum."
}