Date of this Version
Summer 4-20-2026
Document Type
Article
Citation
Almoqren, N., & Alrashoud, M. (2025). LLM-driven active learning for dependency analysis of mobile app requirements through contextual reasoning and structural relationships. Applied Sciences, 15(18), 9891. https://doi.org/10.3390/app15189891
Bi, Z., Chen, J., Jiang, Y., Xiong, F., Guo, W., Chen, H., & Zhang, N. (2024). Codekgc: Code language model for generative knowledge graph construction. ACM Transactions on Asian and Low-Resource Language Information Processing, 23(3), 1–16. https://doi.org/10.1145/3641850
Erfani, A., & Khanjar, H. (2025). Large language models for construction risk classification: A comparative study. Buildings, 15(18), 3379. https://doi.org/10.3390/buildings15183379
Hogan, A., Blomqvist, E., Cochez, M., D’Amato, C., Melo, G. D., Gutierrez, C., Kirrane, S., Gayo, J. E. L., Navigli, R., Neumaier, S., Ngomo, A.-C. N., Polleres, A., Rashid, S. M., Rula, A., Schmelzeisen, L., Sequeda, J., Staab, S., & Zimmermann, A. (2022). Knowledge graphs. ACM Computing Surveys, 54(4), 1–37. https://doi.org/10.1145/3447772
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. https://doi.org/10.48550/ARXIV.2005.11401
Mandal, P. S., & Mandal, S. (2024). Insights on tools for knowledge graphs in library and information science. Pearl : A Journal of Library and Information Science, 18(4), 244–248. https://doi.org/10.5958/0975-6922.2024.00027.X
Mandal, P. S., & Mandal, S. (2025). Knowledge graph embedding in library and information services. Journal of Library and Information Communication Technology, 14(1), 59–64. https://doi.org/10.5958/2456-9399.2025.00006.X
Meesad, P., & Mingkhwan, A. (2024). Knowledge graphs in smart digital libraries. In P. Meesad & A. Mingkhwan, Libraries in Transformation (Vol. 157, pp. 327–389). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-69216-1_9
Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., & Miller, A. (2019). Language models as knowledge bases? Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2463–2473. https://doi.org/10.18653/v1/D19-1250
Tiddi, I., & Schlobach, S. (2022). Knowledge graphs as tools for explainable machine learning: A survey. Artificial Intelligence, 302, 103627. https://doi.org/10.1016/j.artint.2021.103627
Wang, C., Liu, X., & Song, D. (2020). Language models are open knowledge graphs. arXiv. https://doi.org/10.48550/ARXIV.2010.11967
Ye, H., Zhang, N., Chen, H., & Chen, H. (2022). Generative knowledge graph construction: A review. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 1–17. https://doi.org/10.18653/v1/2022.emnlp-main.1
Zhong, L., Wu, J., Li, Q., Peng, H., & Wu, X. (2024). A comprehensive survey on automatic knowledge graph construction. ACM Computing Surveys, 56(4), 1–62. https://doi.org/10.1145/3618295
Abstract
Structured Abstract
Purpose - Knowledge graphs play a key role in modern library and information services for information discovery, advanced search, and explainable recommendation systems. Recent progress in generative and large language models (LLMs) is changing. The present paper presents a clear and concise overview of how these models support knowledge graph construction in library and information science.
Design/methodology/approach –This study shows a conceptual and analytical approach. It considers the latest trends in generative models and LLMs as applied to the construction of knowledge graphs. Their application in entity extraction, relation identification, schema mapping, and triple generation on unstructured text is reviewed in the paper. An effective model is suggested, incorporating both data-based generation and symbolic verification to enhance reliability.
Findings - Generative models and LLMs are much more efficient in terms of knowledge graph building. The proposed hybrid framework is helpful in solving the data quality, consistency, and trust problems.
Originality - The paper emphasizes a middle path of combining generation and validation. It contributes to emerging research on intelligent and trustworthy knowledge infrastructures for libraries.
Research limitations/implications –The present paper deals with a conceptual analysis and does not include empirical evaluation. Future research is needed to assess performance, bias, and scalability across different library collections and languages.
Practical implications - Suggested framework offers better metadata enrichment, semantic discovery, authority control, and reference services.
Social implications - The proposed solution can automate the creation of large-scale knowledge graphs with limited technical resources in libraries. The framework may be implemented in digital libraries and institutional repositories.
