From Textbooks to Chatbots: Applying Large Language Models in Vietnamese History Learning
Nguyen Nang Hung Van, Ngo Van Uc, Pham Van Quan, Truc Thanh Tran, Phan Thanh Tra, Truc Thi Kim Nguyen · 2025
In the era of digital transformation, the integration of Large Language Models (LLMs) into education has opened new avenues for interactive and effective learning. This paper introduces the development of a chatbot designed to support learning Vietnamese history by using advanced LLM to deliver accurate and contextually appropriate responses. The chatbot employs modern natural language processing (NLP) techniques, including the Vietnamese Bi-Encoder and Meta-LLaMA models, to convert historical textbook content into a structured and conversational format. Data was sourced from Vietnamese history textbooks for grades 6 to 12, systematically organized into a database, and processed using embedding and retrieval mechanisms to enable seamless question-answer interactions. Built on the Django framework, the system provides a user-friendly interface and a scalable back-end for diverse educational applications. Initial evaluations indicate the chatbot’s high accuracy and relevance in answering historical queries, enhancing both user engagement and accessibility. This project not only supports historical education but also promotes Vietnamese cultural heritage through the application of artificial intelligence. Future developments include expanding the dataset, incorporating multilingual capabilities, and optimizing the user experience, further establishing the chatbot as a valuable tool for learning and preserving history.