Quy trình sử dụng AI tạo sinh hỗ trợ giáo viên thiết kế bài tập lập trình tích hợp thuật toán phục vụ bồi dưỡng học sinh giỏi môn tin học trung học phổ thông: Minh họa ở chủ đề đồ thị
Tóm tắt
Generative artificial intelligence (GenAI) can support teachers in designing programming exercises; however, AI-generated outputs still require careful review before being used in teaching. This study adopts a design-oriented approach with illustrative case analysis and proposes a five-step process for using GenAI to support the design of programming exercises that integrate multiple algorithms. Two cases were analyzed: Floyd-Warshall combined with permutation enumeration, and BFS combined with dynamic programming for counting shortest paths. The design process was carried out using ChatGPT; the source problems, prompts provided to the AI, and the initial and revised outputs were compared according to six criteria: correctness and feasibility, alignment with instructional objectives, degree of algorithm integration, appropriateness of difficulty, potential for creating differentiated task levels, and anticipated readiness for classroom use. The results indicate that initial AI-generated outputs may merely juxtapose independent requirements or contain technical limitations. Through iterative teacher review and revision, the exercises were refined to better align with the intended integration goals. The findings reported here are based on the authors’ analysis of two illustrative cases and have not yet been independently validated.
Tài liệu tham khảo
Burke, C. M. (2025). AI-assisted exam variant generation: A human-in-the-loop framework for automatic item creation. Education Sciences, 15(8), 1029. https://doi.org/10.3390/educsci15081029
Choi, S., Jeong, S., Park, S., Kim, Y., & Han, I. (2026). Analyzing teacher-AI interaction patterns across teacher experience and AI proficiency in student-centered lesson design. Teaching and Teacher Education, 169, 105266. https://doi.org/10.1016/j.tate.2025.105266
Del Carpio Gutierrez, A., Denny, P., & Luxton-Reilly, A. (2024). Evaluating automatically generated contextualised programming exercises. In Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1 (pp. 289-295). ACM. https://doi.org/10.1145/3626252.3630863
Denny, P., Sarsa, S., Hellas, A., & Leinonen, J. (2022). Robosourcing educational resources - Leveraging large language models for learnersourcing. In Proceedings of the Workshop on Learnersourcing: Student-Generated Content @ Scale 2022 (Vol. 3410, pp. 3-19). CEUR Workshop Proceedings. https://doi.org/10.48550/arXiv.2211.04715
Elnaffar, S., Rashidi, F., & Abualkishik, A. Z. (2026). Teaching with AI: A systematic review of chatbots, generative tools, and tutoring systems in programming education. International Journal of Learning, Teaching and Educational Research, 25(1), 1-28. https://doi.org/10.26803/ijlter.25.1.1
Frankford, E., Höhn, I., Sauerwein, C., & Breu, R. (2024). A survey study on the state of the art of programming exercise generation using large language models. In 2024 36th International Conference on Software Engineering Education and Training (CSEE&T) (pp. 1-5). IEEE. https://doi.org/10.1109/CSEET62301.2024.10662990
Freitas, T. C., Costa Neto, A., Pereira, M. J. V., & Henriques, P. R. (2023). NLP/AI based techniques for programming exercises generation. In 4th International Computer Programming Education Conference (ICPEC 2023) (Vol. 112, pp. 9:1-9:12). Schloss Dagstuhl - Leibniz-Zentrum für Informatik. https://doi.org/10.4230/OASIcs.ICPEC.2023.9
Jordan, M., Ly, K., & Soosai Raj, A. G. (2024). Need a programming exercise generated in your native language? ChatGPT’s got your back: Automatic generation of non-English programming exercises using OpenAI GPT-3.5. In Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1 (pp. 618-624). ACM. https://doi.org/10.1145/3626252.3630897
Kali, Y., McKenney, S., & Sagy, O. (2015). Teachers as designers of technology enhanced learning. Instructional Science, 43(2), 173-179. https://doi.org/10.1007/s11251-014-9343-4
Nguyễn Thế Dũng (2024). Cơ hội và thách thức khi sử dụng AI chatbot trong dạy học lập trình: Nghiên cứu trường hợp ở khu vực miền Trung và Tây Nguyên. Tạp chí Giáo dục, 24(7), 49-54. https://tcgd.tapchigiaoduc.edu.vn/index.php/tapchi/article/view/1632
Nguyễn Thế Dũng (2026). Đề xuất mô hình dạy học đồng sáng tạo kết hợp con người - TRIZ - AI chatbot trong dạy học Tin học. Tạp chí Giáo dục, 26(13), 78-84. https://tcgd.tapchigiaoduc.edu.vn/index.php/tapchi/article/view/4815
Sarsa, S., Denny, P., Hellas, A., & Leinonen, J. (2022). Automatic generation of programming exercises and code explanations using large language models. In Proceedings of the 2022 ACM Conference on International Computing Education Research (pp. 27-43). ACM. https://doi.org/10.1145/3501385.3543957
Ta, N. B. D., Nguyen, H. G. P., & Gottipati, S. (2026). Automatic generation of introductory programming exercises with large language models. Research and Practice in Technology Enhanced Learning, 21, 025. https://doi.org/10.58459/rptel.2026.21025
Wang, Z., Liu, M., & Islam, A. Y. M. A. (2026). Reimagining teacher-AI co-design in learning task design: Trends and perspectives. Humanities and Social Sciences Communications, 13, 757. https://doi.org/10.1057/s41599-026-06981-y
Zheng, X., Lin, H., Cai, S., Yang, Y., Zheng, Z., & Liang, Y. (2026). UniCode: Augmenting evaluation for code reasoning. In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026). https://doi.org/10.48550/arXiv.2510.17868
Zhu, M., Xu, L., & Ericson, B. (2025). A systematic review of research on large language models for computer programming education [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2506.21818
Đã Xuất bản
Cách trích dẫn
Số
Chuyên mục
Giấy phép
Bản quyền (c) 2026 Tạp chí Giáo dục
Tác phẩm này được cấp phép theo Ghi nhận tác giả của Creative Commons Giấy phép quốc tế 4.0 .









