MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extraction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916946230902784 |
|---|---|
| author | Li, Zhongqiu Wang, Shiquan Fang, Ruiyu Bao, Mengjiao Wu, Zhenhe Song, Shuangyong Li, Yongxiang He, Zhongjiang |
| author_facet | Li, Zhongqiu Wang, Shiquan Fang, Ruiyu Bao, Mengjiao Wu, Zhenhe Song, Shuangyong Li, Yongxiang He, Zhongjiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09082 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extraction Li, Zhongqiu Wang, Shiquan Fang, Ruiyu Bao, Mengjiao Wu, Zhenhe Song, Shuangyong Li, Yongxiang He, Zhongjiang Computation and Language 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. |
| title | MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extraction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.09082 |