Large Language Models for Ontology Engineering: A Systematic Literature Review

Ontology engineering (OE) is a complex task in knowledge representation that relies heavily on domain experts to accurately define concepts and precise relationships in a domain of interest, as well as to maintain logical consistency throughout the resultant ontology. Recent advancements in Large Language Models (LLMs) have created new opportunities to automate and enhance various stages of ontology development. This paper presents a systematic literature review on the use of LLMs in OE, focusing on their roles in core development activities, input-output characteristics, evaluation methods, and application domains. We analyze 30 different papers to identify common tasks where LLMs have been applied, such as ontology requirements specification, implementation, publication, and maintenance. Our findings indicate that LLMs serve primarily as ontology engineers, domain experts, and evaluators, using models such as GPT, LLaMA, and T5 to process heterogeneous inputs (such as OWL ontologies, text, competency questions, etc.) to generate task-specific outputs (such as examples, axioms, documentation, etc.). Our review also observed a lack of homogenization in task definitions, dataset selection, evaluation metrics, and experimental workflows. At the same time, some papers do not release complete evaluation protocols or code, making their results hard to reproduce and their methods insufficiently transparent. Therefore, the development of standardized benchmarks and hybrid workflows that integrate LLM automation with human expertise will become an important challenge for future research.