Search papers, labs, and topics across Lattice.
This paper introduces the INTERNAL STUDENT DIALOGUE (INSIDE) framework, which fine-tunes large language models (LLMs) to simulate not only student actions but also their underlying reasoning processes. By generating internal dialogues based on Bloom's Taxonomy and training on paired think traces and actions, INSIDE enhances the fidelity of simulated student behavior in educational contexts. The results indicate significant improvements in both action fidelity and reasoning alignment, with the model achieving up to 57.9% alignment across evaluations, addressing a critical gap in existing LLM-based simulators.
INSIDE reveals that LLMs can be fine-tuned to think like students, not just act like them, significantly enhancing simulation fidelity in educational applications.
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%.
