提出统一发现等价与包含关系的新框架，让系统一次搞定两种语义匹配。
AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching
- 用多智能体协作的LLM框架，逐步探索目标本体找匹配
- 在混合任务中表现优异，且在单一任务上也优于传统方法
- 首次构建支持混合匹配的基准数据集，推动本体对齐发展
本体匹配（OM）传统上被分为等价发现和包含匹配两类，现有系统只能识别其中一种语义对应关系。本文提出新型混合本体匹配（HOM）任务，统一等价与包含关系的发现，并设计基于大语言模型的多智能体框架AgentMap。给定源本体中的概念，AgentMap通过语义检索、层次搜索与协同多智能体推理，逐步探索目标本体，若存在则识别等价概念，否则找到最细粒度的包含者。我们进一步扩展了四个本体匹配数据集以构建HOM基准，并在混合、仅等价、仅包含三种设置下评估AgentMap。实验表明，该框架在混合设置下表现优异，且在仅等价与仅包含设置下分别超越等价匹配和包含匹配基线。
原文摘要 · Abstract (English)
Ontology matching (OM) has traditionally been formulated as either equivalence discovery or subsumption matching. The existing OM systems identify only one type of semantic correspondence and cannot simultaneously discover equivalence and subsumption mappings. In this paper, we introduce Hybrid Ontology Matching (HOM), a new OM task that unifies equivalence and subsumption discovery, and accordingly propose a Large Language Model (LLM)-based multi-agent OM framework AgentMap that is implemented by a series of interdependent semantic decisions. Given a concept in the source ontology, AgentMap integrates semantic retrieval, hierarchical search, and collaborative multi-agent LLM reasoning to progressively explore the target ontology, identifying either the equivalent concept, if one exists, or the most fine-grained subsumer. We further extend four OM datasets for a HOM benchmark and evaluate AgentMap under hybrid, equivalence-only, and subsumption-only settings. Experimental results show that AgentMap achieves promising performance on the hybrid setting, and at the same time outperforms equivalence matching and subsumption matching baselines on the equivalence-only and subsumption-only settings, 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。