Towards Reducing Foreign Language Anxiety Using Level-Appropriate Embodied Conversational Agents

📄 arXiv: 2607.21887v1 📥 PDF

作者: Krishan Rajaratnam, Wenbin Gan, Yuan Sun

分类: cs.HC, cs.CL

发布日期: 2026-07-24

备注: 8 pages, 6 figures, published in the proceedings of EDULEARN26

期刊: K. Rajaratnam, W. Gan, Y. Sun (2026) TOWARDS REDUCING FOREIGN LANGUAGE ANXIETY USING LEVEL-APPROPRIATE EMBODIED CONVERSATIONAL AGENTS, EDULEARN26 Proceedings, Article 1459

DOI: 10.21125/edulearn.2026.1459


💡 一句话要点

提出多代理体对话系统以降低外语焦虑问题

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 外语焦虑 第二语言习得 对话系统 多代理体 语言模型 CEFR 教育技术

📋 核心要点

  1. 外语焦虑(FLA)在第二语言学习中普遍存在,尤其在口语交流中,现有方法未能有效解决这一问题。
  2. 本文提出了一种基于多代理体的对话系统,能够根据学习者的语言能力生成适当难度的对话,旨在降低FLA。
  3. 初步实验结果显示,所提系统生成的对话句子87.4%符合学习者的CEFR水平,显著优于传统系统的54.1%。

📝 摘要(中文)

外语焦虑(FLA)在第二语言习得(SLA)中是一个主要障碍,尤其在对话场景中。随着大型语言模型(LLMs)的普及,研究表明与LLM代理的互动可以在外语教育中发挥重要作用,尤其是降低FLA。本文提出了一种新颖的多代理体对话系统,为英语学习者生成适合其水平的对话,基于欧洲语言共同参考框架(CEFR)定义的语言能力水平。通过“生成-评估-再生成”循环,该系统能够适应用户的语言能力,初步实验结果显示,该系统生成的对话句子更符合学习者的自我评估水平。尽管未能统计显著降低FLA水平,但为未来研究提供了可用性和文化设计的见解。

🔬 方法详解

问题定义:本文旨在解决外语学习者在对话中面临的外语焦虑(FLA)问题。现有方法通常使用复杂的语言,导致学习者感到压力,无法有效交流。

核心思路:论文提出的多代理体对话系统通过生成适合学习者水平的对话,降低其在交流中的焦虑感。系统利用“生成-评估-再生成”的循环机制,确保输出内容与学习者的语言能力相匹配。

技术框架:该系统包括多个LLM代理和一个水平分类器,首先生成对话内容,然后评估其难度,最后根据评估结果进行再生成,以达到适应性输出。

关键创新:最重要的创新在于使用多代理体协同工作,能够动态调整对话难度,显著提升了对话的适应性和有效性。这与传统的单一代理方法形成鲜明对比。

关键设计:系统设计中,关键参数包括CEFR水平分类标准,损失函数用于评估生成内容的适宜性,网络结构则采用了多层次的LLM架构,以增强生成内容的多样性和准确性。

🖼️ 关键图片

img_0
img_1
img_2

📊 实验亮点

实验结果显示,所提多代理体系统生成的对话句子中,有87.4%符合学习者的CEFR水平,显著高于传统系统的54.1%。尽管未能统计显著降低FLA水平,但为未来研究提供了重要的可用性和设计见解。

🎯 应用场景

该研究的潜在应用领域包括外语教育、语言学习应用程序和智能教育系统。通过降低学习者的外语焦虑,能够提升他们的学习效果和交流自信心,未来可能对教育技术的发展产生深远影响。

📄 摘要(原文)

Foreign language anxiety (FLA) can be a major barrier to second language acquisition (SLA), especially in conversational contexts. With the proliferation of large language models (LLMs) throughout all areas of life, recent work suggests that interacting with LLM agents can be instrumental within the field of SLA and foreign language education, especially for reducing FLA. Related work also suggests that linguistic demands and task complexity can be predictors of FLA, implying that the use of demanding, complex language could lead to learners experiencing higher FLA. In this paper, we propose a novel multi-agent embodied conversational system that generates level-appropriate dialogue for English language learners. These levels are based on those defined by the Common European Framework of Reference for Languages (CEFR) to describe non-native listener and speaker proficiency. Using a "generate-evaluate-regenerate" loop with multiple LLM agents and a level classifier, it achieves a desired simplicity that is adaptive to the user's proficiency level. We also share the results of a preliminary small-sample pilot study that tested this system with Japanese university students, to see whether it would yield lower FLA levels than an unsimplified embodied conversational agent. Analysis of conversational output showed that 87.4% of dialogue sentences generated by the proposed multi-agent system fell within one predicted CEFR level of the learner's self-assessed proficiency, compared to 54.1% for the unsimplified agent. This suggests that the novel system is better able to produce output at an appropriate level for the learner. Though this study did not yield statistically significant evidence that the system reduces FLA levels in Japanese learners of English, likely due to a small sample size, it provides usability findings and culturally-informed design insights that will inform future study.