Impact of Guidance and Interaction Strategies for LLM Use on Learner Performance and Perception
This research addresses the challenge of optimizing LLM interactions for educational settings, particularly in large classrooms, though it is incremental in exploring specific guidance strategies.
The study investigated how different guidance strategies for using large language models (LLMs) as teaching assistants affect learner performance and perceptions, finding that direct LLM answers slightly improved performance while refining student solutions increased trust, and structured guidance reduced random queries and copy-pasting.
Personalized chatbot-based teaching assistants can be crucial in addressing increasing classroom sizes, especially where direct teacher presence is limited. Large language models (LLMs) offer a promising avenue, with increasing research exploring their educational utility. However, the challenge lies not only in establishing the efficacy of LLMs but also in discerning the nuances of interaction between learners and these models, which impact learners' engagement and results. We conducted a formative study in an undergraduate computer science classroom (N=145) and a controlled experiment on Prolific (N=356) to explore the impact of four pedagogically informed guidance strategies on the learners' performance, confidence and trust in LLMs. Direct LLM answers marginally improved performance, while refining student solutions fostered trust. Structured guidance reduced random queries as well as instances of students copy-pasting assignment questions to the LLM. Our work highlights the role that teachers can play in shaping LLM-supported learning environments.