用语法库控制聊天机器人输出，精准匹配学习者水平。
Grammar Control in Dialogue Response Generation for Language Learning Chatbots
- 将对话生成模型与教学语法库结合实现语法可控。
- 策略性解码让Llama3在容忍小幅质量下降时优于GPT-3.5。
- 适合语言学习平台和二语习得研究者使用。
基于大语言模型的聊天机器人为语言学习者提供了低成本的对话练习机会，但难以根据学习者当前需求（如特定语法）进行语言形式控制。本文通过将对话响应生成模型与教学语法知识库关联，实现对聊天机器人输出语法的精准控制，并探索该控制如何帮助学习者产出特定语法结构。我们系统评估了提示、微调和解码策略在语法控制对话生成中的表现。结果显示，策略性解码的Llama3在可接受轻微响应质量损失的前提下，性能优于GPT-3.5。模拟实验预测，语法控制的回复能有效支持依据学习者水平定制的语法习得。该方法对现有语言学习聊天机器人及第二语言习得研究具有实际应用价值。代码已开源。
原文摘要 · Abstract (English)
Chatbots based on large language models offer cheap conversation practice opportunities for language learners. However, they are hard to control for linguistic forms that correspond to learners' current needs, such as grammar. We control grammar in chatbot conversation practice by grounding a dialogue response generation model in a pedagogical repository of grammar skills. We also explore how this control helps learners to produce specific grammar. We comprehensively evaluate prompting, fine-tuning, and decoding strategies for grammar-controlled dialogue response generation. Strategically decoding Llama3 outperforms GPT-3.5 when tolerating minor response quality losses. Our simulation predicts grammar-controlled responses to support grammar acquisition adapted to learner proficiency. Existing language learning chatbots and research on second language acquisition benefit from these affordances. Code available on GitHub.
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。