Enhancing Chinese Character Writing Learning: The Role of MLLM-based Intelligent Tutoring Systems
Baohua Su, Qiying Chen, Jun Peng, Wuqiong Tan, Liting Wang · 2025
MLLM-based Intelligent Tutoring System (ITS) improves learning performance by offering corrective feedback. However, a few studies have focused on its role in teaching Chinese as a foreign language. Given the significant impact of feedback on second language acquisition, this study aims to assess the performance of an Intelligent Tutoring System as a Chinese character learning tool. Specifically, we designed an Intelligent Tutoring System for Chinese character learning, which is grounded in a Multimodal Large Language Model with a feedback mechanism based on feedback literacy principles. We then conducted a Chinese teaching experiment to validate the system's effectiveness. Our findings indicate that students using ITS receive more timely corrective feedback and perform better in writing Chinese characters than in the traditional teaching method. These findings offer insights into the importance of corrective feedback in Chinese character learning and the combination of an Intelligent Tutoring System and a Large Language Model.11Funding 1: This research was financially supported by the General Project of the National Social Science Foundation of Education (Project No: BBA23006 3). Funding 2: This paper was the phase research result of the General Project of Education of the National Social Science Foundation of China in 2023, “Cross -contextual Statistical Learning Mechanisms in the Symbiotic Development of Adolescents' Verbal Reasoning and Mental Theory” (No. BBA230063). Funding 3: This paper was supported by the National Innovation and Entre-preneurship Training Program for Undergraduate (No. 202410559051). Funding 4: This paper was supported by the Jinan University Zhong Chen Yulan Research Innovation Project Program for Undergraduate (No. ZC2405).