Enhanced Self-Learning with Epistemologically-Informed LLM Dialogue

2026-04-12

AI Summary

This study addresses the challenge learners face in engaging in deep, meaningful dialogue and processing complex information when using large language models (LLMs) for self-directed learning. To this end, it introduces CausaDisco, a novel dialogue system that systematically integrates Aristotle’s Four Causes epistemological framework into LLM prompting. By generating contextually coherent follow-up questions, CausaDisco guides users toward multidimensional and in-depth inquiry. In a controlled experiment with 36 participants, CausaDisco significantly outperformed baseline systems in enhancing learner engagement, stimulating exploratory behaviors, and fostering multifaceted reasoning. These findings demonstrate the efficacy and innovative potential of grounding LLM-based educational tools in classical epistemological theories.

Technology Category

• Machine Learning: Causal Learning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• self-learning
• large language models
• epistemology
• cognitive load
• dialogue-based interaction

Innovation

• epistemological frameworks
• Four Causes
• LLM-based dialogue
• self-learning
• cognitive support