PulseAugur
实时 20:51:41
English(EN) Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners

可控语音对话生成:面向K-12非母语英语学习者的LLM驱动评分系统

研究人员开发了一个新的LLM驱动框架,用于适应非母语环境中K-12英语学习者的口语对话生成。该系统利用中国国家课程,通过四级评分系统控制词汇复杂度,并整合了分级词汇表和对话语料库等新资源。核心创新是DDPO算法,一种基于GRPO的方法,可在保持多样性的同时优化对话质量,在自然度和教学价值方面优于现有方法。 AI

影响 为根据学习者熟练程度量身定制的个性化英语口语练习提供了一个可扩展的开源平台。

排序理由 学术论文,详细介绍了LLM驱动的教育工具的新算法和框架。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

可控语音对话生成:面向K-12非母语英语学习者的LLM驱动评分系统

报道来源 [2]

  1. arXiv cs.CL TIER_1 English(EN) · Haidong Yuan, Haokun Zhao, Wanshi Xu, Songjun Cao, Qingyu Zhou, Long Ma, Hongjie Fan ·

    Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners

    arXiv:2604.22542v1 Announce Type: new Abstract: 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 …

  2. arXiv cs.CL TIER_1 English(EN) · Hongjie Fan ·

    Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners

    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, us…