Impact of Multimodal and Conversational AI on Learning Outcomes and Experience

TL;DR

This study investigates how multimodal and conversational AI systems affect learning outcomes in STEM education, finding that multimodal, conversational AI enhances learning and experience, but perceptions may not always align with actual learning gains.

Contribution

It provides empirical evidence on the combined effects of multimodality and conversationality in AI-based learning tools, highlighting their impact on cognitive load and learning effectiveness.

Findings

MuDoC led to highest post-test scores and positive experiences.

TexDoC was more engaging but resulted in lower test scores.

Multimodality increases germane load, improving learning outcomes.

Abstract

Multimodal Large Language Models (MLLMs) offer an opportunity to support multimedia learning through conversational systems grounded in educational content. However, while conversational AI is known to boost engagement, its impact on learning in visually-rich STEM domains remains under-explored. Moreover, there is limited understanding of how multimodality and conversationality jointly influence learning in generative AI systems. This work reports findings from a randomized controlled online study (N = 124) comparing three approaches to learning biology from textbook content: (1) a document-grounded conversational AI with interleaved text-and-image responses (MuDoC), (2) a document-grounded conversational AI with text-only responses (TexDoC), and (3) a textbook interface with semantic search and highlighting (DocSearch). Learners using MuDoC achieved the highest post-test scores and reported the most positive learning experience. Notably, while TexDoC was rated as significantly more engaging and easier to use than DocSearch, it led to the lowest post-test scores, revealing a disconnect between student perceptions and learning outcomes. Interpreted through the lens of the Cognitive Load Theory, these findings suggest that conversationality reduces extraneous load, while visual-verbal integration induced by multimodality increases germane load, leading to better learning outcomes. When conversationality is not complemented by multimodality, reduced cognitive effort may instead inflate perceived understanding without improving learning outcomes.