ConnectED: A Curriculum-Aligned AI System for Vietnamese Instructional Lesson Planning and Student Learning

Thang Doan Viet, Anh Nguyen Hoang, Tinh Luong Son, Anh Hoang Thi Ngoc, Huyen Giang Thi Thu, Tai Le Quy — arXiv preprint (2026).

Synthesis

ConnectED is a human-centered AI system supporting the full instructional lifecycle in Vietnamese education: curriculum-aligned lesson design, interactive student learning, and feedback-driven refinement, built on VietEduQwen, a Vietnamese educational LLM trained with SFT and DPO.

The system operationalizes the ADDIE framework through structured prompt templates aligned with Vietnam's Official Dispatch No. 5512/BGDDT-GDTrH, where each phase is both a generation step and a teacher validation gate — keeping teachers in the loop.

On 3,119 questions from the 2025 Vietnamese National High School Examination, VietEduQwen achieved 87.02% accuracy, outperforming Qwen3-8B by 6.10 percentage points; teacher (n=18) and student (n=214) surveys showed strong satisfaction with curriculum alignment and lesson clarity.

The Evaluation phase closes the loop by connecting student performance data to iterative lesson improvement, exemplifying curriculum-grounded, multilingual, and teacher-governed LLM deployment in a Global South context.

Connected Concepts

K 12 AI Education

Teacher AI Competency

Bias Mitigation

Culturally Relevant Pedagogy

Connected Articles

Human LLM Collaborative Coding K12 Educator AI — Human-LLM Collaborative Inductive Coding for Conceptualizing K-12 Educator AI Use

LLM Cultural Relevance K12 — LLMs for Culturally Relevant K-12 Pedagogy

Concept Catalyst Engineering Scaffolds — Creating Learning Scaffolds for Engineering Design Using Concept Catalyst

Agent Voice Accents K12 Group Learning — Exploring How Agent Voice Accents Shape Human-AI Collaboration in K-12 Group Learning

Agreement Not Quality LLM Coding Verification — Agreement Is Not Quality: Blind Expert Verification of Human and LLM Qualitative Coding When Human Consensus Is Not Ground Truth

Cyberscholar GenAI Writing Feedback — Generative AI Feedback, English Writing and Teacher Rubrics: A Multiple-Case Study of CyberScholar

Citation

Doan Viet, T., Nguyen Hoang, A., Luong Son, T., Hoang Thi Ngoc, A., Giang Thi Thu, H., & Le Quy, T. (2026). ConnectED: A curriculum-aligned AI system for Vietnamese instructional lesson planning and student learning. arXiv:2607.28647.