RUIE：基于检索的大语言模型统一信息抽取
RUIE: Retrieval-based Unified Information Extraction using Large Language Model
AI总结：
RUIE是一个基于检索的统一信息抽取框架，利用上下文学习和新颖的示范选择机制，作为可训练的通用插件，在八个数据集上平均F1分数分别提升19.22和3.22。
摘要：
统一信息抽取（UIE）旨在从非结构化文本中抽取多种结构化信息。尽管大语言模型（LLMs）在统一信息抽取方面展现出潜力，但它们需要大量的计算资源，并且往往难以泛化到未见过的任务。我们提出了RUIE（基于检索的统一信息抽取），这是一个利用上下文学习实现高效任务泛化的框架。RUIE引入了一种新颖的示范选择机制，该机制结合了LLM的偏好与关键词增强的奖励模型，并采用了一个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可作为各种LLM的通用插件。在八个保留数据集上的实验结果表明了RUIE的有效性，与指令微调方法和其他检索器相比，平均F1分数分别提升了19.22和3.22。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
