Can Large Language Model-Based Chatbots Support Sustainable AI-Enhanced Education? Evidence from Young Learners’ Conceptions

Understanding learners’ conceptions of artificial intelligence (AI)-supported learning can inform the sustainable integration of AI into education. This study examined primary school students’ conceptions of large language model-based (LLM-based) chatbots-supported learning and explored differences associated with learning motivation. Seventy-two students participated in learning activities designed around the CLEAR prompt-engineering framework. A mixed-methods approach combined the draw-and-write technique with questionnaires assessing learning motivation, self-efficacy, and critical thinking tendencies. Students represented LLM-based chatbots as resources supporting a range of learning activities. Exploratory comparisons indicated motivation-related differences in the representation of learning content, usage times, and locations. Students with lower learning motivation more frequently depicted specific learning content and home-based use, whereas those with higher learning motivation more frequently depicted classroom-based use. Students with higher learning motivation also reported significantly higher self-efficacy, while no statistically significant between-group difference was found in critical thinking tendencies. By integrating young learners’ draw-and-write representations with questionnaire data and motivation-based comparisons, this study extends existing research by providing learner-centered evidence on how primary school students conceptualize LLM-based chatbot-supported learning and how these conceptions vary according to learning motivation. The findings may inform differentiated instructional guidance and learner-responsive task design that support purposeful and responsible AI use, contributing a learner-centered perspective to the development of inclusive and sustainable AI-enhanced learning environments.