@inproceedings{kirsch-etal-2025-pm3,
    title = "{PM}3-{KIE}: A Probabilistic Multi-Task Meta-Model for Document Key Information Extraction",
    author = "Kirsch, Birgit  and
      Allende-Cid, H{\'e}ctor  and
      Rueping, Stefan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.1075/",
    pages = "20890--20912",
    ISBN = "979-8-89176-256-5",
    abstract = "Key Information Extraction (KIE) from visually rich documents is commonly approached as either fine-grained token classification or coarse-grained entity extraction. While token-level models capture spatial and visual cues, entity-level models better represent logical dependencies and align with real-world use cases.We introduce PM3-KIE, a probabilistic multi-task meta-model that incorporates both fine-grained and coarse-grained models. It serves as a lightweight reasoning layer that jointly predicts entities and all appearances in a document. PM3-KIE incorporates domain-specific schema constraints to enforce logical consistency and integrates large language models for semantic validation, thereby reducing extraction errors.Experiments on two public datasets, DeepForm and FARA, show that PM3-KIE outperforms three state-of-the-art models and a stacked ensemble, achieving a statistically significant 2{\%} improvement in F1 score."
}