@inproceedings{liu-etal-2026-prouie,
    title = "{P}ro{UIE}: A Macro-to-Micro Progressive Learning Method for {LLM}-based Universal Information Extraction",
    author = "Liu, Wenda  and
      Zhigang, Song  and
      Nie, Shuai  and
      Liu, Guangyao  and
      Chen, Lisung  and
      Yang, Binyu  and
      Chen, Yaran  and
      Zhou, Peng  and
      Wang, Hongzhen  and
      Liu, Yuchen  and
      Hu, Wenyue  and
      Xu, Jiaming  and
      Shi, Runyu  and
      Huang, Ying",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings 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.findings-acl.1093/",
    pages = "21737--21750",
    ISBN = "979-8-89176-395-1",
    abstract = "LLM-based universal information extraction (UIE) methods often rely on additional information beyond the original training data, which increases training complexity yet often yields limited gains. To address this, we propose ProUIE, a Macro-to-Micro progressive learning approach that improves UIE without introducing any external information. ProUIE consists of three stages: (i) macro-level Complete Modeling (CM), which learns NER, RE, and EE along their intrinsic difficulty order on the full training data to build a unified extraction foundation, (ii) meso-level Streamlined Alignment (SA), which operates on sampled data with simplified target formats, streamlining and regularizing structured outputs to make them more concise and controllable, and (iii) micro-level Deep Exploration (DE), which applies GRPO with stepwise fine-grained rewards (SFR) over structural units to guide exploration and improve performance. Experiments on 36 public datasets show that ProUIE consistently improves unified extraction, outperforming strong instruction-tuned baselines on average for NER and RE while using a smaller backbone, and it further demonstrates clear gains in production-oriented information extraction."
}