Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation
This work addresses the need for better student simulation tools for educators in online education, though it is incremental as it builds on existing LLM methods.
The paper tackles the problem of simulating student learning behaviors in online education by addressing the lack of datasets with annotated course materials and the difficulty of processing long textual data. It introduces a transferable iterative reflection (TIR) module that enhances LLMs to achieve more accurate simulation than classical deep learning models, even with limited data.
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.