Requirements for Verification Results of Educational Materials Generated by AI

Aim. To present a set of requirements helping to visualise AI results for monitoring the compliance of educational materials with regulatory requirements, ensuring their effective integration into the practical activities of a teacher.

Methodology. The research is based on the analysis of regulatory legal documents, as well as on the theoretical understanding of approaches and principles outlined in works devoted to Explainable artificial intelligence (XAI), the digital educational environment, and pedagogical design. The key method was system analysis, which made it possible to synthesise requirements for the interface of the educational content verification system from various sources.

Results. A set of requirements for displaying the results of educational materials verification has been formulated and substantiated, including: a multi-window interface for simultaneously displaying the lesson plan, identified inconsistencies, regulatory references, and AI recommendations, high-precision rendering of mathematical expressions, transparent visualization of AI (XAI) logic to enhance teacher trust, integrated symbolic and spatial representation of educational content, cognitive load management through visual analytics, and engagement monitoring features and risk management indicators.

Research implications. The theoretical significance of the work lies in the systematisation and adaptation of XAI requirements and provisions of national standards for the design of educational products with AI algorithms to the task of constructing user interfaces for educational systems using AI technologies. The practical significance consists in the development of a set of specific parameters (resolution, pixel density, colour space, etc.) that can be used in the creation and selection of hardware and software tools for the implementation of intelligent systems in the educational process, increasing their transparency and , the level of trust on the part of teachers as a consequence.

Conclusions. The level of compliance of educational materials developed on the basis of artificial intelligence systems and the effectiveness of their application in the educational process are determined not only by the quality of their algorithms, but also by the thoughtfulness of the user interface. The work formulates and substantiates a set of requirements for the visualisation of the results of such systems, integrating the provisions of Explainable AI, national standards for the use of AI in education, and modern principles of pedagogical design. This set can serve as a regulatory basis for the design of interfaces of educational AI systems.

1. Agaltsova, D. V. & Valkova, Yu. E. (2023). AI Technologies for University Teachers. In: World of Science, Culture and Education, 2 (99), 5–7. DOI: 10.24412/1991-5497-2023-299-5-7 (in Russ.).

2. Biryukov, D. N. & Dudkin, A. S. (2025). Explainability and Interpretability as Important Aspects to Secure Decisions Made by Intelligent Systems (Review Article). In: Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 25 (3), 373–386. DOI: 10.17586/2226-1494-2025-25-3-373-386 (in Russ.).

3. Belov, F. A., Nedogreeva, N. G. & Kopovoy, A. S. (2025). Experimental Aspect of Developing Scientific Literacy. In: Innovative Projects and Programs in Education, 3 (99), 36–42 (in Russ.).

4. Kuzmenko, M. V. (2025). Artificial Intelligence in Research Activities and Academic Writing: An Analytical Review of Areas and Limitations of Application. In: Lifelong Education: The 21st Century, 13 (3), 22–42. DOI: 10.15393/j5.art. 2025.10846 (in Russ.).

5. Kuzmina, E. S. & Goryunov, D. A. (2024). Methods of Text Data Analysis Using Machine Learning. In: Economy and Society, 7 (122), 703–707 (in Russ.).

6. Melnikova, E. V. & Tsvetkova, V. A. (2025). Analysis of the Possibilities of Applying Artificial Intelligence in Modern Science-Metrics and Bibliometrics. In: RSUH/RGGU Bulletin. Series: Information Science. Information Security. Mathematics, 2, 19–40. DOI: 10.28995/2686-679X-2025-2-19-40 (in Russ.).

7. Minakov, A. I. (2024). Artificial Intelligence in Education as a Relevant Direction in the Training of Modern Teachers. In: World of Science. Pedagogy and Psychology, 12 (1). URL: https://mir-nauki.com (accessed: 10.10.2025) (in Russ.).

8. Obydenkov, Yu. N. (2025). The Role of the Teacher in Developing Critical Thinking in Students When Studying Robotics Using a Virtual Environment. In: Innovative Projects and Programs in Education, 3 (99), 65–71 (in Russ.).

9. Obydenkov, Yu. N., Shevchuk, M. V. & Kostyakova, V. G. (2025). Immersion in the Basics of Programming Using Ready-Made Machine Learning and Artificial Intelligence Modules. In: Engineering Education in a Digital Society: Proceedings of the International Scientific and Methodological Conference (Minsk, March 14, 2024). Minsk: Belarusian State University of Informatics and Electronics publ., pp. 270–273 (in Russ.).

10. Osadchuk, E. V. On the Main Development Directions of Artificial Intelligence Technologies as a Tool for Scientific Research. In: Science Management: Theory and Practice, 7, 147–157. DOI: 10.19181/smtp.2025.7.1.10 (in Russ.).

11. Pak, N. I., Syromyatnikov, A. A. & Stepanova, T. A., et al. (2024). Visualization of the Procedure for Assessing the Quality of the Digital Educational Environment Using the “Transparent Box” Model. In: RUDN Journal of Informatization in Education, 21 (1), 86–104. DOI: 10.22363/2312-8631-2024-21-1-86-104 (in Russ.).

12. Rozov, K. V. (2022). Formation of Professional Readiness of Future Computer Science Teachers to Use Artificial Intelligence Technologies. In: Informatics and Education, 37 (2), 50–63. DOI: 10.32517/0234-0453-2022-37-2-50-63 (in Russ.).

13. Salykova, O. S., Artykbaeva, A. A. & Iskakova, A. M., et al. (2025). Neural Network Methods for Analysing Students’ Text Reviews: Architecture, Training, and Interpretation of Results. In: Bulletin of Shakarim University. Technical sciences, 4 (20), 24–31 (in Russ.). DOI: 10.53360/2788-7995-2025-4(20)-3.

14. Telitsyna, A. Yu. (2024). Optimization of Scientific Activity Through the Integration of Ai: Neural Networks as a Tool in Working with Academic Literature. In: Monitoring of Public Opinion: Economic and Social Changes, 5, 218–236. DOI: 10.14515/monitoring.2024.5.2623 (in Russ.).

15. Shishov, S. E. & Ryakhimova, E. G. (2025). Dialectics of Rivalry and Cooperation in the Professional Identity of a Teacher of Secondary Vocational Education. In: Innovative Projects and Programs in Education, 3 (99), 29–35 (in Russ.).