Saved in:
Bibliographic Details
Main Authors: Cao, Yi-Fan, Shigyo, Kento, Gu, Yitong, Wang, Xiyuan, Liu, Weijia, Wang, Yang, Gotz, David, Zhou, Zhilan, Qu, Huamin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.10545
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915933417635840
author Cao, Yi-Fan
Shigyo, Kento
Gu, Yitong
Wang, Xiyuan
Liu, Weijia
Wang, Yang
Gotz, David
Zhou, Zhilan
Qu, Huamin
author_facet Cao, Yi-Fan
Shigyo, Kento
Gu, Yitong
Wang, Xiyuan
Liu, Weijia
Wang, Yang
Gotz, David
Zhou, Zhilan
Qu, Huamin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10545
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhanced Self-Learning with Epistemologically-Informed LLM Dialogue
Cao, Yi-Fan
Shigyo, Kento
Gu, Yitong
Wang, Xiyuan
Liu, Weijia
Wang, Yang
Gotz, David
Zhou, Zhilan
Qu, Huamin
Human-Computer Interaction
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.
title Enhanced Self-Learning with Epistemologically-Informed LLM Dialogue
topic Human-Computer Interaction
url https://arxiv.org/abs/2604.10545