Abstract

Large Language Models (LLMs) have sparked a drastic improvement in the ways computers can understand, process, and generate language. As LLM-based offerings become mainstream, we explore the incorporation of such LLMs into introductory or undergraduate database systems education. Students and instructors are both faced with the calculator dilemma: while the use of LLM-based tools may “solve” tasks such as assignments and exams, do they impede or accelerate the learning itself? We review deficiencies of using existing off-the-shelf tools for learning, and further articulate the differentiated needs of database systems students as opposed to trained data practitioners. Building on our exploration, we outline a vision that integrates LLMs into database education in a principled manner, keeping pedagogical best practices in mind. If implemented correctly, we posit that LLMs can drastically amplify the impact of existing instruction, minimizing costs and barriers towards learning database systems fundamentals.

Updated: