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

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.

26 pages

References in corpus (21)

• Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation
• "What It Wants Me To Say": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models
• MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' Journaling
• Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education
• Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling
• Generating Automatic Feedback on UI Mockups with Large Language Models
• VirtuWander: Enhancing Multi-modal Interaction for Virtual Tour Guidance through Large Language Models
• Understanding the Impact of Long-Term Memory on Self-Disclosure with Large Language Model-Driven Chatbots for Public Health Intervention
• Evaluating the Experience of LGBTQ+ People Using Large Language Model Based Chatbots for Mental Health Support
• ChaCha: Leveraging Large Language Models to Prompt Children to Share Their Emotions about Personal Events
• Supporting Self-Reflection at Scale with Large Language Models: Insights from Randomized Field Experiments in Classrooms
• C2Ideas: Supporting Creative Interior Color Design Ideation with Large Language Model
• ABScribe: Rapid Exploration & Organization of Multiple Writing Variations in Human-AI Co-Writing Tasks using Large Language Models
• CodeTailor: LLM-Powered Personalized Parsons Puzzles for Engaging Support While Learning Programming
• MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention
• Memoro: Using Large Language Models to Realize a Concise Interface for Real-Time Memory Augmentation
• Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation
• pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
• CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Models
• simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing
• ReactGenie: A Development Framework for Complex Multimodal Interactions Using Large Language Models