arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.10317cs.AI
收藏

LLMs4OM:使用大语言模型匹配本体

LLMs4OM: Matching Ontologies with Large Language Models

TIB Leibniz Information Centre for Science and Technology(TIB莱布尼茨科学与技术信息中心)

Hamed Babaei Giglou, Jennifer D'Souza, Felix Engel, Sören Auer

AI总结:

提出LLMs4OM框架,利用双模块和零样本提示评估大语言模型在本体匹配任务中的有效性,在20个数据集上表现匹配或超越传统系统。

摘要:

本体匹配(Ontology Matching, OM)是知识集成中的一项关键任务,对齐异构本体有助于实现数据互操作性和知识共享。传统OM系统通常依赖专家知识或预测模型,对大语言模型(LLMs)潜力的探索十分有限。我们提出了LLMs4OM框架,这是一种评估LLMs在OM任务中有效性的新方法。该框架利用两个模块分别进行检索和匹配,并通过跨三种本体表示(概念、概念-父节点和概念-子节点)的零样本提示进行增强。通过对来自不同领域的20个OM数据集进行全面评估,我们证明LLMs在LLMs4OM框架下能够匹配甚至超越传统OM系统的性能,特别是在复杂匹配场景中。我们的结果突显了LLMs为OM领域做出重大贡献的潜力。

英文摘要:

Ontology Matching (OM), is a critical task in knowledge integration, where aligning heterogeneous ontologies facilitates data interoperability and knowledge sharing. Traditional OM systems often rely on expert knowledge or predictive models, with limited exploration of the potential of Large Language Models (LLMs). We present the LLMs4OM framework, a novel approach to evaluate the effectiveness of LLMs in OM tasks. This framework utilizes two modules for retrieval and matching, respectively, enhanced by zero-shot prompting across three ontology representations: concept, concept-parent, and concept-children. Through comprehensive evaluations using 20 OM datasets from various domains, we demonstrate that LLMs, under the LLMs4OM framework, can match and even surpass the performance of traditional OM systems, particularly in complex matching scenarios. Our results highlight the potential of LLMs to significantly contribute to the field of OM.

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。

↑