Development of an intelligent conversational assistant with dynamic selection of neural language models and a knowledge retrieval mechanism

This paper presents the development of an intelligent conversational assistant designed to support users in obtaining and clarifying information about university class schedules. The evolution of dialogue systems is considered, from early rule-based text dialogue programs based on pattern matching of input utterances to modern virtual assistants implemented using neural transformer architectures and large language models. The relevance of the study is determined by the use of large language models in combination with Retrieval-Augmented Generation (RAG), which makes it possible to generate responses based on information retrieved from external sources. An architecture of an intelligent conversational assistant has been developed that integrates a RAG mechanism, dynamic routing between several neural language models, and automatic updating of the knowledge base through parsing Admiral F. F. Ushakov State Maritime University web resources. The proposed approach ensures robust processing of variable user queries and response generation based on the retrieved context. Unlike existing solutions that rely on a fixed language model, the proposed architecture implements adaptive selection of a generative model depending on the type of user query. A method for domain-oriented context construction for processing dynamically updated tabular schedule data has been developed, including specialized web page parsing, semantic structuring of the extracted information, and prompt engineering rules. To improve the factual reliability of responses, a mechanism is proposed that constrains generation to the retrieved data and applies terminological filtering. An ETL pipeline for updating the knowledge base has been implemented, enabling automatic updating of information about university class schedules. A comparative study of the effectiveness of the Qwen, GigaChat, and DeepSeek language models in processing user queries within the considered subject domain has been conducted. The obtained results demonstrate improved response accuracy and confirm the effectiveness of the proposed conversational assistant architecture.

1. Vaswani, A., I. Polosukhin et al. "Attention is All you Need." Advances in Neural Information Processing Systems – 30. Curran Associates, Inc., 2017.

2. Minaee, Shervin, et al. "Large Language Models: A Survey." arXiv, 2025. Web. 08 Jan. 2026 . <https:// arxiv.org/abs/2402.06196>.

3. Zhao, Wayne Xin, et al. "A Survey of Large Language Models." arXiv, 2026. Web. 08 Jan. 2026 <https:// arxiv.org/abs/2303.18223>.

4. Kaddour, Jean, et al. "Challenges and Applications of Large Language Models." arXiv, 2023. Web. 08 Jan. 2026 .

5. Wang, F., S. Wang et al. "A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness." ACM Trans. Intell. Syst. Technol. 16.6 (2025). DOI: 10.1145/3768165.

6. Wang, Z., W. Zhang et al. "History, development, and principles of large language models: an introductory survey." AI and Ethics 5.3 (2025): 1955–1971. DOI: 10.1007/s43681-024-00583-7.

7. Liu, Y., L. Jin et al. "Datasets for large language models: a comprehensive survey." Artificial Intelligence Review 58.12 (2025): 403. DOI: 10.1007/s10462-025-11403-7.

8. Jin, Y., L. Ma et al. "Efficient multimodal large language models: a survey." Visual Intelligence 3.1 (2025): 27. DOI: 10.1007/s44267-025-00099-6.

9. Gao, Yunfan, et al. "Retrieval-Augmented Generation for Large Language Models: A Survey." arXiv, 2024. Web. 08 Jan. 2026 <https://arxiv.org/abs/2312.10997>.

10. Lála, Jakub, et al. "PaperQA: Retrieval-Augmented Generative Agent for Scientific Research." arXiv, 2023. Web. 08 Jan. 2026 <https://arxiv.org/abs/2312.07559>.

11. Naveed, H., A. Mian et al. "A Comprehensive Overview of Large Language Models." ACM Trans. Intell. Syst. Technol. 16.5 (2025). DOI: 10.1145/3744746.

12. Antonov, I. V. and Yu. V. Bruttan. "Using rag technology and large language models to search for documents and obtain information in corporate information systems." Computer Research and Modeling 17.5 (2025): 871–888. DOI: 10.20537/2076-7633-2025-17-5-871-888.

13. Mansur, A. M., Zh. Kh. Mokhammad and Yu. A. Kravchenko. "Development of a chatbot for classification and analysis of natural language texts using local large language models." Izvestiya Sfedu. Engineering Sciences 3(245) (2025): 159–171. DOI: 10.18522/2311-3103-2025-3-159-171.

14. Gevorgyan, A. A. and V. A. Kudinov. "Improving interaction with applicants through ai-based chatbots." Auditorium 2(42) (2024): 13–19.

15. Rodionov, A. V. and D. A. Korzh. "Tools for building a chatbot for the admissions commission of an university." System Analysis and Mathematical Modeling 6.3 (2024): 367–376. DOI: 10.17150/2713-1734.2024.6(3).

16. Savkina, A. V. and E. S. Matveev. "Razrabotka klientskoy chasti sistemy dlya realizatsii raboty chatbota." Tendentsii razvitiya nauki i obrazovaniya 115-15 (2024): 107–112. DOI: 10.18411/trnio-11-2024-710.

17. Vertogradov, V. V. and S. V. Shchelokova. "Comparative Competitive Analysis of Generative AI Chatbots in Russia and Worldwide." Studies on Russian Economic Development 36.5 (2025): 643–652. DOI: 10.1134/S1075700725700376.

18. Vol'nikov, M. S. and E. A. Danilov. "Overview of existing chatbot solutions using artificial neural networks: their capabilities, advantages and disadvantages." Sovremennye informatsionnye tekhnologii 39(39) (2024): 9–15.

19. Epryntseva, N. A. "The development of a chatbot in the social network "vkontakte"for an educational organization." Ingineering Journal of Don 9(105) (2023): 656–668.

20. Alekseenko, V. A. and I. A. Tatin. "Development of a chatbot for educational purposes." Information Technology and Mathematical Modeling in The Management of Complex Systems 2(26) (2025): 8–15.

21. Golovko, V., V. Golenkov and M. Kovalev et al. "Approaches of Neuro-Symbolic Integration: Large Language Models and Knowledge Bases." Information Technology and Mathematical Modeling in The Management of Complex Systems 9 (2025): 87–96.

22. Shmat, A. V. "Application of large language models and retrieval-a ugmented generation technology for enterprise assistants." Izvestiya Tula State University 10 (2024): 720–726. DOI: 10.24412/2071-6168-2024-10-720-721.

23. Gerasimenko, E. M., Yu. A. Kravchenko and D. A. Shanenko. "Algorithm for searching and acquisition of knowledge based on technologies for processing and analyzing texts in natural language." Izvestiya Sfedu. Engineering Sciences 5(241) (2024): 88–102. DOI: 10.18522/2311-3103-2024-5-88-102.

24. Ponimash, Z. A. and M. V. Potanin. "Method and algorithm for extracting features from digital signals based on neural networks transformer." Izvestiya Sfedu. Engineering Sciences 6(242) (2024): 52–64. DOI: 10.18522/2311-3103-2024-6-52-64.

25. Andreeva, O. V., E. V. Khekert, M. L. Somko and A. I. Epikhin. "Intelligent management systems and universities in the transport industry: trends and prospects ." World of Transport and Transportation 22.1(110) (2024): 94–99. DOI: 10.30932/1992-3252-2024-22-1-12.

26. Epikhin, A. I., S. I. Kondrat'ev and E. V. Khekert. "Machine learning methods in monitoring the operational behavior of a marine two-stroke diesel engine." Transport of The Russian Federation 3(112) (2024): 50–53.