Advancing Knowledge Together: Integrating Large Language Model-based Conversational AI in Small Group Collaborative Learning
Zhenyao Cai, Seehee Park, Nia Nixon, Shayan Doroudi
Abstract
In today’s educational landscape, students learn collaboratively, where students benefit from both peer interactions and facilitator guidance. Prior research in Human-Computer Interaction (HCI) and Computer-Supported Collaborative Learning (CSCL) has explored chatbots and AI techniques to aid such collaboration. However, these methods often depend on predefined dialogues (which limits adaptability), are not based on collaborative learning theories, and do not fully recognize the learning context. In this paper, we introduce an Large Language Model (LLM)-powered conversational AI, designed to enhance small group learning through its advanced language understanding and generation capabilities. We detail the iterative design process, final design, and implementation. Our preliminary evaluation indicates that the bot performs as designed but points to considerations in the timing of interventions and bot’s role in discussions. The evaluation also reveals that learners perceive the bot’s tone and behavior as important for engagement. We discuss design implications for chatbot integration in collaborative learning and future research directions.