Comparative Performance of GPT-4, RAG-Augmented GPT-4, and Students in MOOCs

Generative Pretrained Transformers (GPT) have significantly improved natural language processing, showcasing enormous versatility across diverse applications. Although GPT models have enormous potential, they frequently encounter issues such as mistakes and hallucinations, which may limit their practical use. Addressing these shortcomings, Retrieval-Augmented Generation (RAG) represents an innovative approach that potentially enhances the accuracy and reliability of these models by leveraging external databases to correct and enrich their outputs. In our study, a RAG-augmented GPT-4 model was tested within an AI-focused Massive Open Online Course (MOOC) and outperformed a standard GPT-4 model, achieving an 85% success rate compared to 81%. Notably, it also surpassed the average student performance, underscoring its ability to deliver precise and contextually relevant responses. These findings suggest the potential of RAG in enhancing AI models for educational use and indicate that instructors can leverage this technology to refine assessment methods and that students can achieve more personalized and engaging learning experiences.