TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students

要旨

Large language models (LLMs) can empower teachers to build pedagogical conversational agents (PCAs) customized for their students. As students have different prior knowledge and motivation levels, teachers must review the adaptivity of their PCAs to diverse students. Existing chatbot reviewing methods (e.g., direct chat and benchmarks) are either manually intensive for multiple iterations or limited to testing only single-turn interactions. We present TeachTune, where teachers can create simulated students and review PCAs by observing automated chats between PCAs and simulated students. Our technical pipeline instructs an LLM-based student to simulate prescribed knowledge levels and traits, helping teachers explore diverse conversation patterns. Our pipeline could produce simulated students whose behaviors correlate highly to their input knowledge and motivation levels within 5% and 10% accuracy gaps. Thirty science teachers designed PCAs in a between-subjects study, and using TeachTune resulted in a lower task load and higher student profile coverage over a baseline.

著者
Hyoungwook Jin
KAIST, Daejeon, Korea, Republic of
Minju Yoo
Ewha Womans University, Seoul, Korea, Republic of
Jeongeon Park
University of California San Diego, La Jolla, California, United States
Yokyung Lee
KAIST, Daejeon, Korea, Republic of
Xu Wang
University of Michigan, Ann Arbor, Michigan, United States
Juho Kim
KAIST, Daejeon, Korea, Republic of
DOI

10.1145/3706598.3714054

論文URL

https://dl.acm.org/doi/10.1145/3706598.3714054

動画

会議: CHI 2025

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2025.acm.org/)

セッション: Technology in Education and Academic Practice

G303
5 件の発表
2025-04-30 23:10:00
2025-05-01 00:40:00
日本語まとめ
読み込み中…