AI-Assistant Development and Integration into Learning Management System
Ekaterina Andreevna KARAVAEVA,
Vladimir Igorevich VASILEVSKIJ,
Georgy Mikhailovich LANIN,
Dmitrii Sergeevich PROKUDIN https://doi.org/10.15514/ISPRAS-2025-37(4)-25
Abstract
The ongoing digitalization of education requires new ways of presenting information and attention retention mechanisms. The aim of the presented work is to propose a solution for implementing a large language model, which will interactively generate prompts of different types, within an e-learning course on programming. The main approaches are the analysis of existing relatively small language models, the TOPSIS method to select the most appropriate one, prototyping, and the integration of the proposed software solution with the HEI educational system. As a result, a service that can be integrated into learning management systems is presented. The paper also presents the results of testing the models that formed the basis of the presented solution.
About the Authors
Ekaterina Andreevna KARAVAEVA
Scientific and Educational Laboratory of Cloud and Mobile Technologies,
Higher School of Economics (HSE)
Russian Federation
Russian Federation
A research intern at the Laboratory of Cloud and Mobile Technologies, Faculty of Computer Science, National Research University Higher School of Economics. Her research interests include cloud technologies, algorithms, and data structures.
Vladimir Igorevich VASILEVSKIJ
Scientific and Educational Laboratory of Cloud and Mobile Technologies,
Higher School of Economics (HSE)
Russian Federation
Russian Federation
A research intern at the Laboratory of Cloud and Mobile Technologies, Faculty of Computer Science, National Research University Higher School of Economics. His research interests include cloud technologies and code generation.
Georgy Mikhailovich LANIN
Department of Software Engineering Higher School of Economics (HSE)
Russian Federation
Russian Federation
A 2nd year student of the System and Software Engineering program at the Department of Software Engineering, Faculty of Computer Science, National Research University Higher School of Economics. His research interests include systems analysis and multi-agent systems.
Dmitrii Sergeevich PROKUDIN
Lomonosov Moscow State University
Russian Federation
Russian Federation
Specialist of the Department of mathematical methods of forecasting of CMC of Lomonosov Moscow State University. His research interests include pattern recognition.
References
1. M. A. Razafinirina, W. G. Dimbisoa, and T. Mahatody, “Pedagogical alignment of large language models (llm) for personalized learning: a survey, trends and challenges,” Journal of Intelligent Learning Systems and Applications, vol. 16, pp. 448–480, 2024.
2. R. E. Wang, A. T. Ribeiro, C. D. Robinson, S. Loeb, and D. Demszky, “Tutor copilot: a human-ai approach for scaling real-time expertise,” arXiv preprint arXiv:2410.03017, 2024.
3. T. Phung et al., “Automating human tutor-style programming feedback: leveraging gpt-4 tutor model for hint generation and gpt-3.5 student model for hint validation,” in Proceedings of the 14th Learning Analytics and Knowledge Conference, 2024, pp. 12–23.
4. L. Roest, H. Keuning, and J. Jeuring, “Next-step hint generation for introductory programming using large language models,” in ACE ’24: Proceedings of the 26th Australasian Computing Education Conference, 2024, pp. 144–153.
5. Data for article: prompts and answers. (Online). Доступно по ссылке: https://github.com/sage-hse/data_for_article
6. M. AI, “Llama 3 technical report,” https://ai.meta.com/llama/, 2024, accessed: 2025-04-10.
7. M. Riviere, S. Pathak, P. G. Sessa, and et al., “Gemma 2: Improving open language models at a practical size,” arXiv preprint arXiv:2408.00118, 2024. (Online). Доступно по ссылке: https://arxiv.org/abs/2408.00118
8. A. Yang, B. Yang, B. Cao, and et al., “Qwen2: Scaling up and distilling down open multilingual language models,” arXiv preprint arXiv:2403.16473, 2024. (Online). Доступно по ссылке: https://arxiv.org/abs/2403.16473
9. E. Roszkowska, “Multi-criteria decision-making models by applying the topsis method to crisp and interval data,” in Multiple Criteria Decision Making. Springer International Publishing, 2011, pp. 7–11.
Supplementary files
Review
For citations:
KARAVAEVA E.A., VASILEVSKIJ V.I., LANIN G.M., PROKUDIN D.S. AI-Assistant Development and Integration into Learning Management System. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2025;37(4):175-190. https://doi.org/10.15514/ISPRAS-2025-37(4)-25
Email this article 