In this project, a simulation method for predicting the learner's performance, a learning content generation method based on the learning simulation, and a learning environment for learning by teaching with the learner's copy model are developed to support the learner automatically. The core technology is a copy learner model, which imitates the learners' sentence generation process using a large-scale language model and is used for understanding detailed learning status. Based on the copy learner model, the learning system developed in this project integrates learning assessment, learning content generation, and a peer learning environment to automate the loop with the assessments, the content generation, and the support.
2025.09: Keynote in ICLEA2025
2025.04: The paper about performance prediction using LLM has been aceepted by AIED2025. Note-Driven RAG for Learner Performance Estimation via Controlling LLM Knowledge
2024.10: The paper about detuning method has been aceepted by CELDA2024. Tsubasa Minematsu, Atsushi Shimada, Large Language Model Detuning in Learning Content Understanding
2023.10: Research has started.