No-code approach to building semantic networks by means of prompt engineering
DOI:
https://doi.org/10.20535/2411-1031.2025.13.2.344712Keywords:
semantic knowledge modeling, large language models , cybersecurity, OSINT, text analytics, formal control primitives, prompt engineering, ntological modelingAbstract
The article proposes a no-code approach to building semantic networks by means of prompt engineering using large language models (LLMs). A framework is developed in which the basic primitives – condition, loop, and function – are combined into compositional structures that ensure automated extraction of concepts, establishment of links between them, and construction of formalized knowledge graphs. The proposed method relies on the no-code principle, which makes it possible to describe algorithmic logic in natural language without involving program code. This enables the use of large language models not only as text generators but as full-fledged tools for constructing knowledge structures. Within the study, an LLM is considered as a driver for automated ontology engineering. The model interprets natural-language instructions as formalized actions, which makes it possible to iteratively extract key concepts, determine types of relations, and form knowledge graphs with a given logical sequence. Particular attention is paid to the field of cybersecurity, where rapid creation and updating of threat ontologies is crucial for timely response to new attack vectors. The practical implementation of the approach is carried out on the example of building a semantic network in the topic of phishing attacks. In the course of the experiment, the GPT-5 language model processed 48 news reports, automatically forming about 70 pairs of related concepts. The resulting knowledge graph reflected an integral structure of the domain, where the central concept “phishing” is combined with numerous derivative terms: cyberattack, social engineering, spoofed page, malicious software, etc. The results of the experiment prove that the proposed methodology ensures the relevance of inter-concept relations and the enrichment of the basic terminology with semantically related concepts. The integration of large language models into the process of ontological modeling simplifies the creation of knowledge structures, lowers the entry barrier for users without programming experience, and opens up prospects for the development of neuro-symbolic systems that combine the generative capabilities of models with formal methods of knowledge representation. The proposed approach has high potential for practical application in fields that require dynamic knowledge updating – primarily in cybersecurity, medicine, financial technologies, and data analytics.
References
A.S. Lippolis et al., “Ontology generation using large language models”, in Proc. 22nd Eur. Semantic Web Conf. (ESWC 2025), Portoroz, Slovenia, 2025, pp. 321-341. doi: https://doi.org/10.1007/978-3-031-94575-5_18.
D. Lande, and L. Strashnoy, “Semantic AI framework for prompt engineering”, SSRN, 14 p., 2025. doi: https://doi.org/10.2139/ssrn.5172867.
L. Beurer-Kellner, M. Fischer, and M. Vechev, “Prompting is programming: A query language for large language models”, in Proc. ACM on Programming Languages, vol., iss. PLDI, art. 186, pp. 1946-1969, 2023. doi: https://doi.org/10.1145/3591300.
C. Shimizu, and P. Hitzler, “Accelerating knowledge graph and ontology engineering with large language models”, J. Web Semantics, vol.85, art. 100862, 2025. doi: https://doi.org/10.1016/j.websem.2025.100862.
R.S. Dehal, M. Sharma, and E. Rajabi, “Knowledge graphs and their reciprocal relationship with large language models”, Mach. Learn. Knowl. Extraction, vol. 7, iss. 2, art. 38, 2025. doi: https://doi.org/10.3390/make7020038.
A. Mavridis, S. Tegos, C. Anastasiou, M. Papoutsoglou, and G. Meditskos, “Large language models for intelligent RDF knowledge graph construction: Results from medical ontology mapping”, Frontiers Artif. Intell., vol. 8, art. 1546179, 2025. doi: https://doi.org/10.3389/frai.2025.1546179.
Y. Xu et al., “LLM-Enhanced framework for building domain-specific lexicon for urban power grid design”, Appl. Sci., vol. 15, iss. 8, art. 4134, 2025. doi: https://doi.org/10.3390/app15084134.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Collection "Information Technology and Security"
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors that are published in this collection, agree to the following terms:
- The authors reserve the right to authorship of their work and pass the collection right of first publication this work is licensed under the Creative Commons Attribution License, which allows others to freely distribute the published work with the obligatory reference to the authors of the original work and the first publication of the work in this collection.
- The authors have the right to conclude an agreement on exclusive distribution of the work in the form in which it was published this anthology (for example, to place the work in a digital repository institution or to publish in the structure of the monograph), provided that references to the first publication of the work in this collection.
- Policy of the journal allows and encourages the placement of authors on the Internet (for example, in storage facilities or on personal web sites) the manuscript of the work, prior to the submission of the manuscript to the editor, and during its editorial processing, as it contributes to productive scientific discussion and positive effect on the efficiency and dynamics of citations of published work (see The Effect of Open Access).
