@inproceedings{hong-etal-2025-system,
    title = "System Report for {CCL}25-Eval Task 11: Enhancing {C}hinese Character Handwriting Evaluation with Multimodal Large Language Models",
    author = "Hong, Xiaoqing  and
      Li, Yunhan  and
      Ni, Lyu",
    editor = "Lin, Hongfei  and
      Li, Bin  and
      Tan, Hongye",
    booktitle = "Proceedings of the 24th {C}hina National Conference on Computational Linguistics ({CCL} 2025)",
    month = aug,
    year = "2025",
    address = "Jinan, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/ingest-ccl/2025.ccl-2.52/",
    pages = "437--443",
    abstract = "``With the development of smart devices, students' ability to handwrite Chinese characters has generally been decreasing. Chinese character handwriting receives increasing attention because the standardization of Chinese character handwriting is one of the most important components of national education in China. Due to inadequate professional teachers and labor-intensive evaluation means, it is difficult to provide large-scale,personalized, and low-latency evaluation feedback in Chinese character handwriting education. Recently, large language models (LLMs) have made outstanding achievements in natural language understanding and generation. Thus, the multimodal large language model(MLLM) is an efficient method to resolve the difficulties. We introduce an enhanced neural network architecture, referred to as ACBAM-VGG16, which is developed by augmenting the CBAM-VGG16 framework with adversarially generated examples. Leveraging this model, we propose customized training and inference mechanisms for MLLMs, specifically targeting two downstream tasks: quality assessment of handwritten Chinese character images and generation of descriptive textual comments. We introduce an effective inference strategy that allows an MLLM to maintain high performance in scenarios where limited training data are available for model fine-tuning, resulting in the average F1 score can be improved by 6.74{\%}. Moreover, we design a hierarchical MLLM fine-tuning framework to ensure the precision and diversity of generated comments. In the comparison of various MLLMs, the proposed framework increases the weighted aver-age of ROUGE-1, ROUGE-2, and ROUGE-L by 2.33{\%}-9.94{\%}.''"
}