Enhanced Self-Learning with Epistemologically-Informed LLM Dialogue

TL;DR

This paper introduces CausaDisco, an LLM-based self-learning system using Aristotle's Four Causes to improve learner engagement and understanding through epistemologically-informed dialogue.

Contribution

It presents a novel approach integrating epistemological frameworks into LLM prompts to enhance self-learning interactions and cognitive support.

Findings

CausaDisco increased learner engagement and exploration.

Participants showed more diverse perspectives with CausaDisco.

The system effectively guided learners through complex topics.

Abstract

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.