ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction

TL;DR

ProUIE introduces a three-stage macro-to-micro progressive learning framework for universal information extraction with LLMs, enhancing performance without external data across diverse datasets.

Contribution

It presents a novel macro-to-micro learning approach that improves UIE by sequentially modeling at different granularities without external information.

Findings

Outperforms instruction-tuned baselines on 36 datasets for NER and RE.

Achieves better results with a smaller backbone.

Shows significant gains in large-scale production-oriented IE.

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 large-scale production-oriented information extraction.