Enhanced Self-Learning with Epistemologically-Informed LLM Dialogue
For self-learners and HCI researchers, this work demonstrates a novel method to enhance LLM-based educational tools by reducing cognitive load and promoting deeper engagement.
The paper introduces CausaDisco, an LLM-based dialogue system that integrates Aristotle's Four Causes framework to improve self-learning by generating coherent follow-up questions. A controlled study (N=36) showed it fostered more engaging interactions and sophisticated exploration compared to a baseline.
Large Language Models (LLMs) have advanced self-learning tools, enabling more personalized interactions. However, learners struggle to engage in meaningful dialogue and process complex information. To alleviate this, we incorporate epistemological frameworks within an LLM-based approach to self-learning, reducing the cognitive load on learners and fostering deeper engagement and holistic understanding. Through a formative study (N=26), we identified epistemological differences in self-learner interaction patterns. Building upon these findings, we present \textit{CausaDisco}, a dialogue-based interactive system that integrates Aristotle's \textit{Four Causes} framework into LLM prompts to enhance cognitive support for self-learning. This approach guides learners' self-learning journeys by automatically generating coherent and contextually appropriate follow-up questions. A controlled study (N=36) demonstrated that, compared to baseline, \textit{CausaDisco} fostered more engaging interactions, inspired sophisticated exploration, and facilitated multifaceted perspectives. This research contributes to HCI by expanding the understanding of LLMs as educational agents and providing design implications for this emerging class of tools.