GenOM: Ontology Matching with Description Generation and Large Language Model

2025-08-14

AI Summary

To address weak semantic interoperability and low matching accuracy across heterogeneous biomedical ontologies, this paper proposes an ontology matching method that synergistically integrates large language models (LLMs) with rule-based exact matching. First, LLMs generate high-quality textual definitions for ontology concepts to enrich semantic representations. Second, embedding models retrieve candidate alignments based on semantic similarity. Third, a rule-driven exact matching strategy—enhanced by few-shot prompting and ablation analysis—is applied for refinement and verification. Evaluated on the OAEI Bio-ML benchmark, our approach significantly outperforms traditional systems and state-of-the-art LLM-based baselines, achieving improvements in precision, robustness, and cross-domain adaptability. The results empirically validate the effectiveness of the “definition generation + semantic embedding + exact verification” collaborative paradigm for biomedical ontology alignment.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Ontology matching (OM) plays an essential role in enabling semantic interoperability and integration across heterogeneous knowledge sources, particularly in the biomedical domain which contains numerous complex concepts related to diseases and pharmaceuticals. This paper introduces GenOM, a large language model (LLM)-based ontology alignment framework, which enriches the semantic representations of ontology concepts via generating textual definitions, retrieves alignment candidates with an embedding model, and incorporates exact matching-based tools to improve precision. Extensive experiments conducted on the OAEI Bio-ML track demonstrate that GenOM can often achieve competitive performance, surpassing many baselines including traditional OM systems and recent LLM-based methods. Further ablation studies confirm the effectiveness of semantic enrichment and few-shot prompting, highlighting the framework's robustness and adaptability.

Problem

• Enhancing semantic interoperability in biomedical ontology matching
• Improving alignment precision with LLM-generated concept definitions
• Combining embedding models and exact matching for robust performance

Innovation

• Generates textual definitions for ontology concepts
• Uses embedding model to retrieve alignment candidates
• Incorporates exact matching tools for precision