Lin-Zucker, M., Bellassen, J., & Zucker, J. D. (2026). Prompting Large Language Models for CEFR-EBCL-Aligned Chinese L2 Learning: An Empirical Study of Sinographic Constraint Compliance. Journal of Technology and Chinese Language Teaching, 17(1), 1-29.
[林季苗, 白樂桑, & 諸葛梁. (2026). 透過提示工程引導大型語言模型進行符合 CEFR–EBCL 標準的漢語第二語言學習：一項關於漢字限制遵循性的實證研究. 科技与中文教学 (Journal of Technology and Chinese Language Teaching), 17(1), 1-29.]

Full paper

Abstract/摘要：

Large Language Models (LLMs) are increasingly used in Chinese as a Second Language (L2) learning, yet their ability to comply with pedagogical constraints specific to the Chinese writing system remains underexplored. This study examines whether system prompts aligned with the CEFR–EBCL framework enable LLMs to generate learner-facing Chinese texts that respect sinographic thresholds at the A1, A1+ and A2 levels. We conducted controlled experiments using two models (GPT-4.1 and GPT-4.1-mini) across ten EBCL-related written tasks. Prompt conditions with and without explicit character lists were compared. Model outputs were automatically analyzed to quantify instruction deviation, defined as the proportion of characters outside the target EBCL set. Results indicate that including explicit character lists significantly reduces out-of-list character production at the A1 and A1+ levels, particularly with GPT-4.1. At the A2 level, this effect becomes marginal. These findings provide empirical evidence on the pedagogical value and limits of prompt-based control of ChatGPT outputs for CEFR–EBCL-aligned Chinese L2 learning.

大型語言模型（LLMs）在漢語作為第二語言學習中的應用日益普及，但其是否能有效遵循漢字書寫系統所特有的教學限制，仍缺乏實證研究。本研究探討在 CEFR–EBCL 框架下，系統提示是否能引導大型語言模型在 A1、A1+ 與 A2 級別生成符合漢字門檻的漢語學習文本。研究以 GPT-4.1 與 GPT-4.1-mini 兩種模型為對象，圍繞十項 EBCL 書面語言任務進行受控實驗，比較提示中是否提供明確漢字列表的差異，並以「指令偏離度」量化模型輸出中超出目標漢字集合的比例。結果顯示，在 A1 與 A1+ 級別中，加入漢字列表能顯著降低不符合門檻的漢字生成比例，而在 A2 級別中，此效果趨於有限。本研究為基於提示工程控制ChatGPT輸出、以支援對應 CEFR–EBCL 標準的漢語二語學習，提供了實證依據。