ACL Findings2026
ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction
Wenda Liu, Zhigang Song, Shuai Nie, Guangyao Liu, Lisung Chen, Binyu Yang, Yaran Chen, Peng Zhou, Hongzhen Wang, Yuchen Liu, Wenyue Hu, Jiaming Xu
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 productionoriented information extraction.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on10
- Event Extraction as Machine Reading ComprehensionJian Liu, Yubo Chen, Kang Liu, Wei Bi et al.EMNLP 2020 · 300 citations
- GoLLIE: Annotation Guidelines improve Zero-Shot Information-ExtractionOscar Sainz, Iker García-Ferrero, Rodrigo Agerri, Oier Lopez de Lacalle et al.ICLR 2024 · 168 citations
- GPT-RE: In-context Learning for Relation Extraction using Large Language ModelsZhen Wan, Fei Cheng, Zhuoyuan Mao, Qianying Liu et al.EMNLP 2023 · 132 citations
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity RecognitionWenxuan Zhou, Sheng Zhang, Yu Gu, Muhao Chen et al.ICLR 2024 · 118 citations
- LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language ModelHao Fei, Shengqiong Wu, Jingye Li, Bobo Li et al.NeurIPS 2022 · 114 citations
Related papers
- Easy-to-Hard Learning for Information ExtractionChang Gao, Wenxuan Zhang, Wai Lam, Lidong BingACL Findings 2023 · 8 citations
- RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information ExtractionChengyuan Liu, Fubang Zhao, Yangyang Kang, Jingyuan Zhang et al.EMNLP Findings 2023 · 17 citations
- Universal Information Extraction with Meta-Pretrained Self-RetrievalXin Cong, Bowen Yu, Mengcheng Fang, Tingwen Liu et al.ACL Findings 2023 · 5 citations
- Unified Structure Generation for Universal Information ExtractionYaojie Lu, Qing Liu, Dai Dai, Xinyan Xiao et al.ACL 2022
- Maximal Clique Based Non-Autoregressive Open Information ExtractionBowen Yu, Yucheng Wang, Tingwen Liu, Hongsong Zhu et al.EMNLP 2021 · 14 citations
