Exploring the Impact of an LLM-Powered Teachable Agent on Learning Gains and Cognitive Load in Music Education
Lingxi Jin, Baicheng Lin, Mengze Hong, Kun Zhang, Hyo-Jeong So
TL;DR
This work addresses the challenge of scalable, effective music theory instruction by pairing Learning by Teaching with a large language model–powered Teachable Agent, Chat Melody. In a controlled online experiment with 28 Chinese university students, the TA group engaged in structured dialogue to analyze music, while the control group studied with instructional materials; post-test gains favored the TA condition ($F = 19.98$, $p < .001$) and cognitive-load reports showed reduced mental effort for the TA group ($t = 2.47$, $p < .05$). The study found that cognitive load was mitigated mainly through decreased mental effort, while mental load did not differ significantly between groups. Overall, the results suggest that AI-driven scaffolding based on LBT can enhance music theory learning and support self-directed inquiry, offering a scalable complement to teacher-led instruction in music education.
Abstract
This study examines the impact of an LLM-powered teachable agent, grounded in the Learning by Teaching (LBT) pedagogy, on students' music theory learning and cognitive load. The participants were 28 Chinese university students with prior music instrumental experiences. In an online experiment, they were assigned to either an experimental group, which engaged in music analysis with the teachable agent, or a control group, which conducted self-directed analysis using instructional materials. Findings indicate that students in the experimental group achieved significantly higher post-test scores than those in the control group. Additionally, they reported lower cognitive load, suggesting that the teachable agent effectively reduced the cognitive demands of music analysis tasks. These results highlight the potential of AI-driven scaffolding based on LBT principles to enhance music theory education, supporting teachers in delivering theory-oriented instruction while fostering students' self-directed learning skills.