With the wide application of large language models in language education, their capability boundaries in academic-level error tagging urgently need examination. This study takes 30 Chinese compositions by Korean learners from the HSK Dynamic Composition Corpus, strictly follows the corpus tagging code, and compares ChatGPT (GPT-5.3) with professional teachers in error tagging. Quantitatively, precision, recall, and F1-score evaluate tagging quality. Qualitatively, four typical scenarios are analyzed to explore human-machine differences. Three findings emerge. First, teachers significantly outperform ChatGPT in precision (98.82% vs. 21.61%), recall (93.31% vs. 18.96%), and F1-score (0.96 vs. 0.20). Over half of ChatGPT's errors are format violations, not content misjudgments. Second, ChatGPT's performance declines stepwise from HSK levels A to C, while teachers maintain high precision across levels. In A-level texts, ChatGPT detects subtle errors teachers overlook. Third, both agree on rule-governed explicit errors, but differ in semantic differentiation, cultural judgment, and tagging granularity. This study clarifies the capability boundaries of large language models in academic corpus tagging and provides empirical evidence for human-machine collaborative interlanguage tagging systems.

随着大语言模型在语言教育领域广泛应用，其在学术级偏误标注中的能力边界有待检 验。本研究以HSK动态作文语料库中30篇韩国高级学习者的汉语作文为样本，严格遵循语 料库代码标注规范，系统比较了ChatGPT（GPT-5.3版本）与专业教师偏误标注的性能差 异。研究发现，教师在精确率（98.82%）、召回率（93.31%）及F1值（0.96）上均显著优 于ChatGPT，ChatGPT超半数错标源于格式错误。随HSK等级从A到C，ChatGPT性能阶梯式衰 减，教师则保持高精度。定性分析显示，两者在规则明确偏误上高度一致，但ChatGPT在 语义辨析、文化判断及标注粒度上存在局限。本研究厘清了大语言模型在学术语料库标注 中的能力边界，为人机协同中介语标注体系构建提供了实证依据。

【目 录】
【摘要】
1. 引言
2. 理论背景与相关研究
3. 研究方法
    1) 研究语料
    2) 标注工具与提示词设计
    3) 标注规范与评价指标
4. 结果分析
    1) ChatGPT与教师整体标注性能对比
    2) 不同汉语能力等级的标注差异对比
    3) ChatGPT与教师标注差异的质性与典型例句分析
5. 结论
【参考文献】
【附录】
【논문초록】

• 闫帅(建国大学GLOCAL创新学院副教授) | 이앤슈아이