Teaching Practice of Explainable Feedback in Programming Empowered by Large Language Models

Xinzhi Li; Yixin Zhang; Jingjing Xie; Rui Zhang; Mengmeng Liu; Jing Zhao

doi:10.6918/IJOSSER.202607_9(7).0008

Authors

Xinzhi Li School of Emergency Technology and Management, University of Emergency Management, Langfang 065201, Hebei Province, China
Yixin Zhang School of Emergency Technology and Management, University of Emergency Management, Langfang 065201, Hebei Province, China
Jingjing Xie School of Emergency Technology and Management, University of Emergency Management, Langfang 065201, Hebei Province, China
Rui Zhang School of Emergency Technology and Management, University of Emergency Management, Langfang 065201, Hebei Province, China
Mengmeng Liu School of Emergency Technology and Management, University of Emergency Management, Langfang 065201, Hebei Province, China
Jing Zhao School of Emergency Technology and Management, University of Emergency Management, Langfang 065201, Hebei Province, China

DOI:

https://doi.org/10.6918/IJOSSER.202607_9(7).0008

Keywords:

Large language models; generative artificial intelligence; programming teaching; explainable feedback; natural language processing; cognitive scaffolding.

Abstract

Against the background of artificial intelligence and large language models, undergraduate natural language processing programming tasks often face delayed feedback, interrupted debugging processes, and insufficient result interpretation. This paper analyzes the scaffolding role of generative artificial intelligence in error diagnosis, step-by-step prompting, and autonomous revision, and proposes an explainable feedback approach characterized by “AI-assisted diagnosis, teacher-guided rule constraints, student-led revision, and process-based reflection”. Taking named entity recognition and sentiment analysis as practical tasks, this paper designs an AI-supported feedback process for programming ability development to improve feedback timeliness, strengthen problem-locating and debugging abilities, and enhance the problem-solving experience in complex programming tasks.

Downloads

Download data is not yet available.

References

[1] Ling, J., Zhang, L. L., Chen, H. G., et al. (2025). Application of generative artificial intelligence in computer experiment teaching. Computer Education, (5), 28–32. https://doi.org/10.16512/j.cnki.jsjjy.2025.05.002. (In Chinese)

[2] Yu, H. Y. (2025). Teaching reform and practice of Python programming data analysis empowered by generative AI. Journal of Computer Technology and Education, 13(7), 78–86. https://doi.org/10.12427/jcte2325-0208.20251212. (In Chinese)

[3] Mittal, U., Sai, S., Chamola, V., & Sangwan, D. (2024). A comprehensive review of generative AI for education. IEEE Access, 12, 142733–142759. https://doi.org/10.1109/ACCESS.2024.3468368.

[4] Yao, D. H., Zhong, X. F., & Du, M. (2025). Research on intelligent adaptive teaching model of programming course based on deep learning. Journal of Computer Technology and Education, 13(5), 8–13. https://doi.org/10.12427/jcte2325-0208.20251002. (In Chinese)

[5] Estévez-Ayres, I., Callejo, P., Hombrados-Herrera, M. Á., et al. (2025). Evaluation of LLM tools for feedback generation in a course on concurrent programming. International Journal of Artificial Intelligence in Education, 35(2), 774–790.

[6] Sweller, J. (1988). Cognitive load during problem solving: Effects on learning. Cognitive Science, 12(2), 257–285.

[7] Si, G. D., Peng, L. M., & Zhang, Y. Q. (2023). Design of data structure experiment question bank from the perspective of cognitive load. Computer Education, (4), 173–176. https://doi.org/10.16512/j.cnki.jsjjy.2023.04.044. (In Chinese)

[8] Wang, W. J., Shi, N. F., & Lü, Z. G. (2024). Research on the construction of teaching practice model of "Algorithm Design and Analysis" course based on feedback mode. Computer Application Digest, 40(24), 16–18, 21. (In Chinese)

[9] Li, H., Lin, S., & Ouyang, Y. (2021). Exploration and practice of natural language processing course teaching based on deep learning. Computer Education, (11), 147–151. https://doi.org/10.16512/j.cnki.jsjjy.2021.11.034. (In Chinese)

[10] Ding, X. J. (2024). Teaching reform and exploration of data structure course based on artificial intelligence. In 2024 International Conference on Artificial Intelligence and Digital Libraries (AIDL) (pp. 18–21). Nanjing, China. https://doi.org/10.1109/AIDL66202.2024.00011.

[11] Liu, J., Gao, Y., Yang, L., & Wang, Z. W. (2025). Exploration of computer network practical teaching model empowered by artificial intelligence. Journal of Computer Technology and Education, 13(5), 105–110. https://doi.org/10.12427/jcte2325-0208.20251018. (In Chinese)