Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation

TL;DR

This paper introduces a novel method using large language models augmented with a transferable iterative reflection module to simulate student learning behaviors in online education, addressing data and processing limitations.

Contribution

The paper presents a new TIR module that enhances LLMs for more accurate and dynamic student behavior simulation in online learning environments.

Findings

TIR improves simulation accuracy over classical models.

The approach captures granular learning dynamics.

It enables better modeling of inter-student correlations.

Abstract

Student simulation supports educators to improve teaching by interacting with virtual students. However, most existing approaches ignore the modulation effects of course materials because of two challenges: the lack of datasets with granularly annotated course materials, and the limitation of existing simulation models in processing extremely long textual data. To solve the challenges, we first run a 6-week education workshop from N = 60 students to collect fine-grained data using a custom built online education system, which logs students' learning behaviors as they interact with lecture materials over time. Second, we propose a transferable iterative reflection (TIR) module that augments both prompting-based and finetuning-based large language models (LLMs) for simulating learning behaviors. Our comprehensive experiments show that TIR enables the LLMs to perform more accurate student simulation than classical deep learning models, even with limited demonstration data. Our TIR approach better captures the granular dynamism of learning performance and inter-student correlations in classrooms, paving the way towards a ''digital twin'' for online education.