大模型能模拟不同母语者学英语的偏误，为语言教学提供新工具。
Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases
- 用信息论方法分析大模型模仿不同母语者说英语的模式。
- 模型复现了日、韩、中文母语者在时态和搭配上的真实偏误特征。
- 适合语言教育研究者与AI辅助教学系统开发者参考。
本研究评估大语言模型（LLMs）模拟第二语言（L2）学习者受其母语（L1）干扰的非母语英语表达能力。在对话式访谈中，我们让模型模仿具有特定母语（如日语、泰语、乌尔都语）的L2学习者，覆盖七种语言，并将生成结果与真实学习者数据进行对比。通过信息论和分布密度度量，分析由母语驱动的语言偏误，如指代词使用和回避行为。结果显示，现代大模型（如Qwen2.5、LLAMA3.3、DeepseekV3、GPT-4o）能够复现人类L2学习者中的母语依赖模式，不同语言的影响显著：日语、韩语和汉语对时态一致有明显影响，乌尔都语则影响名词-动词搭配。研究揭示了大模型在L2对话生成与评估方面的潜力，为未来教育应用提供支持。
原文摘要 · Abstract (English)
This study evaluates Large Language Models' (LLMs) ability to simulate non-native-like English use observed in human second language (L2) learners interfered with by their native first language (L1). In dialogue-based interviews, we prompt LLMs to mimic L2 English learners with specific L1s (e.g., Japanese, Thai, Urdu) across seven languages, comparing their outputs to real L2 learner data. Our analysis examines L1-driven linguistic biases, such as reference word usage and avoidance behaviors, using information-theoretic and distributional density measures. Results show that modern LLMs (e.g., Qwen2.5, LLAMA3.3, DeepseekV3, GPT-4o) replicate L1-dependent patterns observed in human L2 data, with distinct influences from various languages (e.g., Japanese, Korean, and Mandarin significantly affect tense agreement, and Urdu influences noun-verb collocations). Our results reveal the potential of LLMs for L2 dialogue generation and evaluation for future educational applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。