Generative AI Revolutionizes Educational Coding: Empirical Validation of Chinese LLMs’ Performance Leap

DOI

10.2991/978-94-6463-750-2_73How to use a DOI?

Keywords

Generative Artificial Intelligence (GAI); Large Language Models (LLMs); Qualitative Coding in Education

Abstract

This study evaluates four LLMs (DeepSeek, Kimi, GPT-4, Claude) in Chinese educational qualitative coding using 65 AI-enhanced teaching cases. DeepSeek outperformed others with 94% accuracy and 0.928 F1 scores, excelling in high-cognitive tasks like pedagogical objective identification. Confusion matrix analysis revealed its superior contextual adaptation, attributed to Chinese corpus optimization, while ChatGPT showed systemic bias and Kimi exhibited fragmented errors. The findings underscore the importance of cultural-contextual alignment in LLM training for educational tasks, advocating for domain-specific model deployment. This research advances generative AI’s application in linguistically nuanced educational environments.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Xiaoqing Zhang
AU  - Shipian Xu
AU  - Zengyi Yu
PY  - 2025
DA  - 2025/06/15
TI  - Generative AI Revolutionizes Educational Coding: Empirical Validation of Chinese LLMs’ Performance Leap
BT  - Proceedings of the 2025 4th International Conference on Educational Innovation and Multimedia Technology (EIMT 2025)
PB  - Atlantis Press
SP  - 729
EP  - 735
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6463-750-2_73
DO  - 10.2991/978-94-6463-750-2_73
ID  - Zhang2025
ER  -