Efficient Visualization of Knowledge Graphs Based on Next-Generation Language Models

Introduction. This paper examines a methodology for the automated extraction and graphical representation of knowledge from unstructured texts using modern language models. Such methods are becoming increasingly relevant because of the growing need to structure information and identify semantic relations that are difficult to capture manually.

Materials and Methods. The proposed approach combines locally deployed language models with specialized relationextraction tools. Local deployment enables data to be processed in a secure environment without reliance on external services. The methodology includes text preprocessing, entity and relation extraction, structuring, and visualization of the resulting knowledge graphs.

Results. Experimental testing on a corpus of Russian-language scientific articles demonstrated that the approach is applicable both to technical descriptions and to texts containing more abstract concepts. The developed web interface supports interactive visualization and comparative analysis of graphs constructed by different models, thereby improving the interpretability of the results. The approach is robust to textual noise and is applicable to scientific, technical, and regulatory tasks.

Discussion. The results show that the proposed methodology is not limited to a single algorithm and permits the combination of direct extraction, specialized models, multi-stage pipelines, and OWL ontologies. The quality of the resulting graphs depends substantially on the structure of the source text, preprocessing accuracy, and the selected postprocessing procedures; interactive visualization facilitates comparison of outputs generated by different models and supports the interpretation of semantic relations.

Conclusions. The proposed approach can be applied to the analysis of scientific, technical, and regulatory texts in a secure local environment. It is a natural continuation of the authors’ previous research on semantic-associative data analysis and synthesis and the associative-ontological approach. Further development should focus on ensemble schemes, logical validation, semantic inference, and integration with formal ontologies, thereby extending its applicability to information retrieval, research support, and complex-system modelling.

1. Fayans A.M. Building an ontology of fundamental concepts based on a transdisciplinary approach. Ontology of Design. 2022;12(4):454–469. (In Russ.) https://doi.org/10.18287/2223-9537-2022-12-4-454-469

2. Volkova I.A., Shamaeva E.D. An excursion into knowledge graphs. International Journal of Open Information Technologies. 2023;11(3):75–83. (In Russ.)

3. Spesivtsev A.V. Fuzzy-probabilistic approach to formalizing and using expert knowledge to evaluate complex objects states. Journal of Instrument Engineering. 2020;63(11):985–994. (In Russ.)

4. Mityakov S.N., Mityakov E.S. Processes machine learning in the tasks of researching innovative processes. Journal of Applied Research. 2020;4(1):6–13. (In Russ.)

5. Girin R.V., Orlov S.P. Object-oriented decomposition of artificial neural network’s program logic. Ontology of designing. 2018;8(1):110–123. (In Russ.)

6. Zakharova O.I., Kuleshov S.V. Development of a graph neural network for processing text data. Artificial Intelligence and Decision Making. 2024;(4):67–78. (In Russ.) https://doi.org/10.14357/20718594240406

7. Napolskikh D.L. Approach to developing a cluster ontology. Ontology of designing. 2024;14(3):355–365. (In Russ.) https://doi.org/10.18287/2223-9537-2024-14-3-355-365

8. Zhilyaev A.A. Ontologies as a tool for creating open multi-agent resource management systems. Ontology of designing. 2019;9(2):261–281. (In Russ.)

9. Kuleshov S.V., Zaitseva A.A., Levashkin S.P. Processing of unstructured information obtained from the Internet using an associative-ontological approach. In: Problems of Telecommunications Engineering and Technologies PTTT2020: XXII International Scientific and Technical Conference; IV Scientific Forum Telecommunications: Theory and Technologies TTT-2020, Samara, November 17–20, 2020. Samara: PGUTI; 2020. P. 7–11. (In Russ.)

10. Tsvetkov V.Ya., Kurdyukov N.S. Informational ontological modeling. Russian Technological Journal. 2025;13(2):18–26. (In Russ.) https://doi.org/10.32362/2500-316X-2025-13-2-18-26

11. Mamedova N.A., Afanasev M.A., Nefedov Yu.V., Urintsov A.I. Ontology of Engineering and Computational Architecture of Multimodal Transport and Logistics Center. Automatic Documentation and Mathematical Linguistics. 2025;59(2):109–123. https://doi.org/10.3103/S0005105525700554

12. Huguet Cabot P.-L., Tedeschi S., Ngonga Ngomo A.-C., Navigli R. RED: a Filtered and Multilingual Relation Extraction Dataset. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023). 2023. arXiv:2306.09802. https://doi.org/10.18653/v1/2023.acl-long.237