ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction
For practitioners of information extraction, ProUIE offers a training-only method to boost UIE performance without extra data or model size, though gains are incremental over existing approaches.
ProUIE improves LLM-based universal information extraction without external data, achieving consistent gains over strong baselines on 36 datasets, including outperforming instruction-tuned models on NER and RE with a smaller backbone.
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 large-scale production-oriented information extraction.