OntoExtend: A Framework for Requirement-driven and Scalable Ontology Extension with LLMs

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Anna Sofia Lippolis, Mohammad Javad Saeedizade, Stefan Schmid, Simon Blattner, Robin Keskisärkkä, Aldo Gangemi, Eva Blomqvist, Andrea Giovanni Nuzzolese
• Venue: arXiv: cs.AI
• Published: 2026-07-20
• Collected: 2026-07-21
• URL: http://arxiv.org/abs/2607.17963v1
• PDF: https://arxiv.org/pdf/2607.17963v1
• DOI: UNKNOWN

Plain-Language Brief

The paper introduces OntoExtend, a framework that uses Large Language Models (LLMs) to extend existing ontologies based on requirements or competency questions. The framework was evaluated on two use cases and found to produce extensions with few structural issues and minimal revisions required before integration.

What the Document Says

• Ontology extension refers to the process of enhancing an existing ontology in response to emerging requirements.
• Large Language Models (LLMs) have shown potential for generating ontologies from scratch, but current approaches lack explicit ties to requirements or reusable core models and provide limited systematic evaluation of LLM outputs.
• The paper presents OntoExtend, a framework that extends ontologies using LLMs in a requirement-driven manner. It uses Retrieval-Augmented Generation (RAG) over relevant input ontologies and competency questions to propose grounded extensions.
• OntoExtend was evaluated on 39 Competency Questions (CQs) from two use cases: Onto-DESIDE, a public EU-project ontology, 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.
• The results suggest that OntoExtend is useful as a drafting assistant for requirement-driven ontology extension in real-world scenarios. It is also sensitive to CQ specificity and modelling profile.

Key Concepts Mentioned

• Ontology Extension
• Large Language Models (LLMs)
• Retrieval-Augmented Generation (RAG)
• Competency Questions (CQs)
• OntoExtend

Claims Made by the Document

• OntoExtend is a useful drafting assistant for requirement-driven ontology extension.
• OntoExtend is sensitive to CQ specificity and modelling profile.

Evidence Used

• The evaluation results of OntoExtend on two use cases.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.