用检索增强方法让大模型高效提取信息，支持新任务快速适配。
RUIE: Retrieval-based Unified Information Extraction using Large Language Model
- 基于上下文学习，通过检索示例提升任务泛化能力。
- 在8个数据集上平均F1提升19.22分，优于指令微调方法。
- 适合需要快速部署、资源受限的文本信息抽取场景。
统一信息抽取（UIE）旨在从非结构化文本中提取多样化的结构化信息。尽管大语言模型（LLMs）在UIE中展现出潜力，但其需大量计算资源，且难以泛化到未见任务。本文提出RUIE（基于检索的统一信息抽取），一种利用上下文学习实现高效任务泛化的框架。RUIE引入新颖的示范选择机制，结合大模型偏好与关键词增强的奖励模型，并采用通过对比学习和知识蒸馏训练的双编码器检索器。作为首个可训练的UIE检索框架，RUIE可作为通用插件适配多种大模型。在8个保留数据集上的实验表明，RUIE相较指令微调方法和其它检索器，平均F1分数分别提升19.22和3.22。
原文摘要 · Abstract (English)
Unified information extraction (UIE) aims to extract diverse structured information from unstructured text. While large language models (LLMs) have shown promise for UIE, they require significant computational resources and often struggle to generalize to unseen tasks. We propose RUIE (Retrieval-based Unified Information Extraction), a framework that leverages in-context learning for efficient task generalization. RUIE introduces a novel demonstration selection mechanism combining LLM preferences with a keyword-enhanced reward model, and employs a bi-encoder retriever trained through contrastive learning and knowledge distillation. As the first trainable retrieval framework for UIE, RUIE serves as a universal plugin for various LLMs. Experimental results on eight held-out datasets demonstrate RUIE's effectiveness, with average F1-score improvements of 19.22 and 3.22 compared to instruction-tuning methods and other retrievers, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。