Augmenting learning experience in Physics Courses (8.01/8.02) using Large Language Models

The following proposal details a twofold initiative to enhance student learning in the Physics Department’s TEAL courses 8.01 and 8.02, which are general institute requirements (GIRs). The plan aims to integrate advancements in Large Language Models (LLMs) in form of an artificial intelligence tutor that offers interactive guidance during the online learning sequences and the general problem solving. Additionally, this proposal seeks to refine the accuracy of these LLMs through effective techniques such as fine-tuning, Retrieval Augmented Generation (RAG), Reinforcement Learning from Human Feedback (RLHF) and combinations of those. Another important but more practical aspect is the exploration of open-source avenues like using Llama2 as LLM to avoid high fees from the commercially available LLMs like OpenAI.