MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extraction

2025-09-10

AI Summary

Large language models (LLMs) struggle with complex pattern descriptions and multi-step reasoning in universal information extraction (UIE), limiting their effectiveness on structured-output tasks. Method: This paper proposes a novel framework integrating multi-perspective reasoning with reinforcement learning (RL). It is the first to embed multi-perspective reasoning into the RL decoding process, employing context-aware action space design and multi-step reward modeling to guide the model in autonomously exploring reasoning paths—shifting from passive extraction to active, goal-directed reasoning. Contribution/Results: The framework achieves significant improvements over state-of-the-art methods across multiple UIE benchmarks. Notably, it demonstrates superior generalization and robustness on high-difficulty structured-output tasks, validating its cross-domain applicability and advancing the paradigm of reasoning-aware UIE.

Technology Category

• Natural Language Processing: Information Extraction
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Large language models (LLMs) demonstrate robust capabilities across diverse research domains. However, their performance in universal information extraction (UIE) remains insufficient, especially when tackling structured output scenarios that involve complex schema descriptions and require multi-step reasoning. While existing approaches enhance the performance of LLMs through in-context learning and instruction tuning, significant limitations nonetheless persist. To enhance the model's generalization ability, we propose integrating reinforcement learning (RL) with multi-perspective reasoning for information extraction (IE) tasks. Our work transitions LLMs from passive extractors to active reasoners, enabling them to understand not only what to extract but also how to reason. Experiments conducted on multiple IE benchmarks demonstrate that MR-UIE consistently elevates extraction accuracy across domains and surpasses state-of-the-art methods on several datasets. Furthermore, incorporating multi-perspective reasoning into RL notably enhances generalization in complex IE tasks, underscoring the critical role of reasoning in challenging scenarios.

Problem

• Enhancing generalization in universal information extraction tasks
• Addressing structured outputs with complex schema descriptions
• Improving multi-step reasoning for information extraction accuracy

Innovation

• Reinforcement learning for information extraction
• Multi-perspective reasoning with LLMs
• Active reasoning instead of passive extraction