Towards Pedagogy-Grounded Conversational AI Tutors for Interest-Based Learning
TL;DR
Results show the IBL prompt reliably integrated learner interests, but exhibited shallow reflection, inconsistent knowledge checks, and surface-level analogies when interests were underspecified.
Abstract
Interest-based learning (IBL) is an educational approach where learners’ interests are used to contextualize learning. IBL can make instruction feel more relevant and lead to improved learning outcomes, but it is difficult for instructors to implement at scale because learner interests are highly varied. Large language models (LLMs) can support IBL through conversational AI tutors that personalize instruction to individual interests. This paper presents a prompt design approach for creating LLM tutors for IBL. We first conducted a literature review to derive pedagogy-grounded strategies for a base tutor prompt, then embedded additional IBL strategies to produce an IBL tutor prompt. We evaluated both prompts via expert review and a human-participants study with undergraduate students. Results show the IBL prompt reliably integrated learner interests, but exhibited shallow reflection, inconsistent knowledge checks, and surface-level analogies when interests were underspecified. We contribute a reusable prompt design pipeline, prompt templates, and evaluation artifacts for designing interest-based AI tutors.