OntoExtend: A Framework for Requirement-driven and Scalable Ontology Extension with LLMs
2026-07-20 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors introduce OntoExtend, a system that helps improve existing ontologies based on specific requirements using large language models (LLMs). Unlike previous methods, their approach links ontology updates directly to clear questions and existing models, making the process more focused and reliable. They tested OntoExtend with real-world examples and found that it produces mostly good suggestions that need only minor edits by experts. This shows OntoExtend can assist people in expanding ontologies efficiently and accurately.
OntologyOntology ExtensionLarge Language Models (LLMs)Retrieval-Augmented Generation (RAG)Competency QuestionsOnto-DESIDEFunctional EvaluationModelling ProfileEU-project OntologyIndustrial Ontology
Authors
Anna Sofia Lippolis, Mohammad Javad Saeedizade, Stefan Schmid, Simon Blattner, Robin Keskisärkkä, Aldo Gangemi, Eva Blomqvist, Andrea Giovanni Nuzzolese
Abstract
Ontology extension refers to the process of enriching an existing ontology in response to emerging requirements, making it more complete. This task is a resource-intensive and error-prone process. Large Language Models (LLMs) have shown promising performance on generating ontologies from scratch, but current approaches rarely tie ontology extension explicitly to requirements or reusable core models, and offer limited, systematic evaluation of LLM outputs. This paper introduces OntoExtend, a requirements-driven framework for ontology extension with LLMs. It uses retrieval-augmented generation (RAG) over relevant input ontologies and requirements in the form of competency questions to propose grounded extensions. We evaluate OntoExtend on 39 CQs from two use cases: a public EU-project ontology, Onto-DESIDE, and an industrial ontology from Bosch. The generated fragments show few structural issues, satisfy all functional evaluation tests, and are rated by ontology engineers as requiring minor to moderate revision before integration. These results suggest that OntoExtend is useful as a drafting assistant for requirement-driven ontology extension in real world scenarios, while remaining sensitive to CQ specificity and modelling profile.