From Prompt to Graph: Comparing LLM-Based Information Extraction Strategies in Domain-Specific Ontology Development
Abstract
Ontologies are essential for structuring domain knowledge, improving accessibility, sharing, and reuse. However, traditional ontology construction relies on manual annotation and conventional natural language processing (NLP) techniques, making the process labour-intensive and costly, especially in specialised fields like casting manufacturing. The rise of Large Language Models (LLMs) offers new possibilities for automating knowledge extraction. This study investigates three LLM-based approaches, including pre-trained LLM-driven method, in-context learning (ICL) method and fine-tuning method to extract terms and relations from domain-specific texts using limited data. We compare their performances and use the best-performing method to build a casting ontology that validated by domian expert.
Keywords
Cite
@article{arxiv.2602.00699,
title = {From Prompt to Graph: Comparing LLM-Based Information Extraction Strategies in Domain-Specific Ontology Development},
author = {Xuan Liu and Ziyu Li and Mu He and Ziyang Ma and Xiaoxu Wu and Gizem Yilmaz and Yiyuan Xia and Bingbing Li and He Tan and Jerry Ying Hsi Fuh and Wen Feng Lu and Anders E. W. Jarfors and Per Jansson},
journal= {arXiv preprint arXiv:2602.00699},
year = {2026}
}
Comments
11 pages,8 figures,3 tables,presented at International Conference on Industry of the Future and Smart Manufacturing,2025