GLaMoR: Consistency Checking of OWL Ontologies using Graph Language Models

2025-04-26

AI Summary

To address the low inference efficiency of OWL ontology consistency checking at scale, the difficulty of modeling logical structure with traditional machine learning, and the limited capability of large language models in structured semantic reasoning, this paper proposes a Graph Language Model (GLM) inference framework. The framework is the first to adapt GLMs to ontology consistency verification, introducing an end-to-end ontology-to-triple-graph encoding paradigm that preserves first-order logical structure while enhancing generalization. By jointly modeling OWL parsing, graph embedding, and serialization, the method achieves 95% accuracy on the NCBO BioPortal dataset, with inference speed 20× faster than state-of-the-art ontology reasoners. The approach thus significantly balances accuracy, efficiency, and scalability—advancing automated ontology validation for large-scale knowledge graphs.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Machine Learning: Graph-based Machine Learning

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Semantic reasoning aims to infer new knowledge from existing knowledge, with OWL ontologies serving as a standardized framework for organizing information. A key challenge in semantic reasoning is verifying ontology consistency. However, state-of-the-art reasoners are computationally expensive, and their efficiency decreases as ontology sizes grow. While classical machine learning models have been explored for consistency checking, they struggle to capture complex relationships within ontologies. Large language models (LLMs) have shown promising results for simple reasoning tasks but perform poorly on structured reasoning. The recently introduced Graph Language Model (GLM) offers a way to simultaneously process graph-structured data and text. This paper proposes GLaMoR (Graph Language Model for Reasoning), a reasoning pipeline that transforms OWL ontologies into graph-structured data and adapts the GLM architecture for consistency checking. We evaluate GLaMoR on ontologies from the NCBO BioPortal repository, converting them into triples suitable for model input. Our results show that the GLM outperforms all baseline models, achieving $95%$ accuracy while being 20 times faster than classical reasoners. The Code is accessible under: https://github.com/JustinMuecke/GLaMoR

Problem

• Efficiently checking consistency in large OWL ontologies
• Overcoming limitations of classical ML in ontology reasoning
• Adapting graph language models for structured semantic reasoning

Innovation

• Uses Graph Language Model for ontology checking
• Transforms OWL ontologies into graph data
• Achieves high accuracy with faster processing