发表机构
Secomus Technology; FPT Software AI Center; Viettel Solutions; Vietnam Ernst & Young Limited Company; Banking Academy of Vietnam; Vietnam Academy of Science and Technology; University of Koblenz（赛科默斯科技; FPT软件人工智能中心; 越南电信解决方案公司; 越南安永有限公司; 越南银行学院; 越南科学技术研究院; 科布伦茨大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出以人为本的AI系统ConnectED，基于VietEduQwen构建，支持越南教育完整教学生命周期，经评估其准确率优于基准模型，可缩短教师备课时间且获师生高满意度。
AI 中文摘要
本文提出ConnectED，这是一个以人为本的AI系统，通过链接与课程对齐的课程设计、交互式学生学习以及反馈驱动的优化，支持越南教育领域的完整教学生命周期。该系统基于VietEduQwen构建，这是一款通过监督微调（supervised fine-tuning）和直接偏好优化（direct preference optimization，DPO）训练的越南教育大语言模型，确保交互具有学术准确性、教学适宜性和学生安全性。ConnectED通过与越南教育部第5512/BGDDT-GDTrH号公文对齐的结构化提示模板实现ADDIE框架，其中每个阶段既是生成步骤也是教师验证关卡。评估阶段通过将学生表现数据与迭代课程改进关联，进一步形成闭环。除课程生成外，该系统还集成了面向学生的交互式环境，可持续收集学习信号以支持教师决策。对2025年越南高中毕业考试的3119道试题评估显示，VietEduQwen的准确率达87.02%，较Qwen3-8B高出6.10个百分点。对18名教师和214名学生的调查显示，各方对课程对齐度、课程清晰度和易用性的满意度较高。实际应用中，教师在参与审核的情况下，备课时间从3至4小时缩短至约30至45分钟。消融研究证实，DPO训练和基于ADDIE的编排均对系统性能有独立贡献，凸显了结构化教师监督对实际部署的重要性。
英文摘要
This paper presents ConnectED, a human-centered AI system that supports the full instructional lifecycle in Vietnamese education by linking curriculum-aligned lesson design, interactive student learning, and feedback-driven refinement. Built on VietEduQwen, a Vietnamese educational large language model trained via supervised fine-tuning and direct preference optimization, the system ensures academically accurate, pedagogically appropriate, and student-safe interactions. ConnectED operationalizes the ADDIE framework through structured prompt templates aligned with Official Dispatch No. 5512/BGDDT-GDTrH, where each phase serves as both a generation step and a teacher validation gate. The Evaluation phase further closes the loop by connecting student performance data with iterative lesson improvement. Beyond lesson generation, the system integrates a student-facing interactive environment, enabling continuous collection of learning signals to support teacher decision-making. Evaluation on 3,119 questions from the 2025 Vietnamese National High School Examination shows that VietEduQwen achieves 87.02% accuracy, outperforming Qwen3-8B by 6.10 percentage points. Surveys of teachers (n=18) and students (n=214) demonstrate strong satisfaction with curriculum alignment, lesson clarity, and usability. In practice, lesson preparation time is reduced from 3--4 hours to approximately 30--45 minutes with teacher-in-the-loop review. Ablation studies confirm that both DPO training and ADDIE-based orchestration contribute independently to system performance, highlighting the importance of structured teacher oversight for practical deployment.
