Date
Publisher
arXiv
Large Language Model (LLM)-based simulators often reproduce observable actions but fail to capture the underlying reasoning behind them. In education, where student simulation is increasingly used for various applications such as evaluating tutoring systems, this gap is especially pronounced. Two students may submit identical submissions for entirely different reasons. We present INTERNAL STUDENT DIALOGUE (INSIDE), a student modeling framework that fine-tunes LLMs not only to act like students but also to think like them. INSIDE generates internal dialogue grounded in Bloom's Taxonomy across cognitive, affective, and action dimensions, and fine-tunes models on paired think traces and actions. We baseline against different prompting frameworks and evaluate on two axes: fidelity of simulated actions and quality of generated internal dialogue. Our evaluations show that INSIDE improves simulation fidelity in both action fidelity, matching code generation of real students, and reasoning alignment, achieving the highest alignment across models up to 57.9%.
Why it matters
LLM-based student simulators often reproduce observable actions but fail to capture the underlying reasoning behind them. In education, this gap is pronounced because two students may submit identical submissions for entirely different reasons.
Key findings
- An AI student simulator closely matched real students' coding work while improving how accurately it reflected their underlying reasoning.
- The new student simulator achieved higher reasoning alignment than other artificial intelligence models and prompting frameworks tested.
- Standard AI student simulators often successfully reproduce observable student behaviors but fail to capture the underlying thinking behind them.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
Study design
