Developing and Evaluating a Large Language Model-Based Automated Feedback System Grounded in Evidence-Centered Design for Supporting Physics Problem Solving

This article describes the development and evaluation of an AI system using a Large Language Model (LLM) to provide automated feedback for physics problem-solving. The system is grounded in Evidence-Centered Design, suggesting a focus on the underlying reasoning and knowledge students use. The research likely assesses the effectiveness of the LLM in providing helpful and accurate feedback.