可控的口语对话生成：一种基于LLM的评分系统用于K-12非母语英语学习者
Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners
AI总结：
本文提出一种基于LLM的评分系统，通过四级分级系统控制词汇复杂度，提升非母语K-12英语学习者的口语对话质量与教学价值。
摘要：
大型语言模型（LLMs）常因能力匹配问题无法满足非母语K-12英语学习者的教学需求。为解决这一普遍挑战，我们引入了与能力匹配的框架，利用中国国家课程（CSE）作为代表案例，通过四级分级系统精确控制词汇复杂度，并提供全面的资源：分级词汇表和多轮对话语料库。我们的核心技术贡献是DDPO算法（多样性驱动策略优化），一种基于GRPO的多轮方法，旨在在优化对话质量的同时保持对话多样性。该方法显著优于传统方法，实现低词汇外率和高多样性，同时提升对话自然度和教学价值。虽然基于CSE，我们的框架设计灵活，可快速适应其他教育标准。我们的模型、数据和代码将全部开源，提供可扩展的个性化英语口语练习平台，有效解决非沉浸式环境中K-12学习者面临的独特挑战。
英文摘要：
Large language models (LLMs) often fail to meet the pedagogical needs of K-12 English learners in non-native contexts due to a proficiency mismatch. To address this widespread challenge, we introduce a proficiency-aligned framework that adapts LLM outputs to learner abilities, using China's national curriculum (CSE) as a representative case. Our framework enables precise control over lexical complexity through a four-tier grading system, supported by a comprehensive suite of new resources: graded vocabulary lists and a multi-turn dialogue corpus. Our core technical contribution is the \textbf{DDPO} algorithm,Diversity Driven Policy Optimization, a multi-turn GRPO-based approach designed to preserve dialogue diversity while holistically optimizing dialogue quality. This method significantly outperforms conventional approaches, achieving low out-of-vocabulary rates and high diversity while enhancing conversational naturalness and pedagogical value. While grounded in the CSE, our framework is designed for flexibility and can be readily adapted to other educational standards. Our models, data, and code will all be open-sourced, providing a scalable platform for personalized English speaking practice that effectively addresses the unique challenges faced by K-12 learners in non-immersive environments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
