Autors: Ivanova, T. I.
Title: New Perspectives of Ontology Alignment Using Large Language Models
Keywords: Large language models, ontology integration, Ontology mapping

Abstract: Ontology mapping is crucial in intelligent systems, as it is the way to make different ontologies interoperable. In this study, we discuss the applicability of large language models (LLMs) to automate the process of mapping and assessing the quality of ontology alignment. We propose an incremental methodology for mapping and assessing the quality of ontology alignment, oriented towards the use of LLMs, and discuss the applicability and results of using LLMs in each step of the ontology mapping process.

References

  1. Y. Y.Cheng, and Y. Xia,”A systematic review of methods for aligning, mapping, merging taxonomies in information sciences.” Journal of Documentation, vol. 79, no.6, 2023, pp. 1413-1439.
  2. X. Liu, Q.Tong, X. Liu, and Z. Qin, “Ontology matching: State of the art, future challenges, and thinking based on utilized information.”, IEEe Access, vol. 9, 2021, pp. 91235-91243.
  3. C. Trojahn, R. Vieira, D. Schmidt, A. Pease, and G. Guizzardi, “Foundational ontologies meet ontology matching: A survey.”, Semantic Web, vol 13, no 4, 2022, pp. 685-704.
  4. J. Gatto, O. Sharif, P. Seegmiller, P., Bohlman, and S. M. Preum, “Text encoders lack knowledge: Leveraging generative llms for domain-specific semantic textual similarity.” arXiv preprint, 2023, arXiv:2309.06541.
  5. S. Xu, Z. Wu, H. Zhao, P. Shu, Z. Liu, W. Liao, and X. Li, “Reasoning before comparison: LLM-enhanced semantic similarity metrics for domain specialized text analysis.” arXiv preprint 2024. arXiv:2402.11398.
  6. J. P. Portisch, “Exploiting general-purpose background knowledge for automated schema matching.” Universitaet Mannheim (Germany), 2022.
  7. Z. Z. Zulkipli, R. Maskat, and N. H. I. Teo, “A systematic literature review of automatic ontology construction.”, Indonesian Journal of Electrical Engineering and Computer Science,vol. 28, no 2, 2022, pp. 878-889.
  8. Y. He, J. Chen, D. Antonyrajah, and I. Horrocks, “BERTMap: a BERT-based ontology alignment system.”, In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, No. 5, 2022, June, pp. 5684-5691.
  9. G. Marvin, N. Hellen, D. Jjingo, and J. Nakatumba-Nabende,”Prompt engineering in large language models.”, In International conference on data intelligence and cognitive informatics, 2023, pp. 387-402. Singapore: Springer Nature Singapore.
  10. P. Sahoo, A. K. Singh, S. Saha, V. Jain, S. Mondal, and A. Chadha, “A systematic survey of prompt engineering in large language models: Techniques and applications.” arXiv preprint 2024. arXiv:2402.07927.
  11. F. N. AL-Aswadi, H. Y. Chan, K. H. Gan, “From ontology to knowledge graph trend: Ontology as foundation layer for knowledge graph”, in: Iberoamerican Knowledge Graphs and Semantic Web Conference, Springer, 2022, pp.330–340

Issue

2025 39th International Conference on Information Technologies, InfoTech 2025 - Proceedings, 2025, Bulgaria, https://doi.org/10.1109/InfoTech67177.2025.11175973

Цитирания (Citation/s):
1. Zhou S., Lin Q., A contrastive learning-based method for cross-cultural semantic alignment in large language models, 2026, Proceedings of SPIE the International Society for Optical Engineering, issue 0, vol. 14128, DOI 10.1117/12.3102736, issn 0277786X, eissn 1996756X - 2026 - в издания, индексирани в Scopus

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus