Exploring the Potential of Large Language Models in Generating Code-Tracing Questions for Introductory Programming Courses
This addresses the need for scalable educational content creation in programming education, though it is incremental as it applies existing LLMs to a specific domain.
The paper tackled generating code-tracing questions for introductory programming courses using GPT4, finding that LLMs can produce diverse questions comparable to human experts based on human evaluation metrics.
In this paper, we explore the application of large language models (LLMs) for generating code-tracing questions in introductory programming courses. We designed targeted prompts for GPT4, guiding it to generate code-tracing questions based on code snippets and descriptions. We established a set of human evaluation metrics to assess the quality of questions produced by the model compared to those created by human experts. Our analysis provides insights into the capabilities and potential of LLMs in generating diverse code-tracing questions. Additionally, we present a unique dataset of human and LLM-generated tracing questions, serving as a valuable resource for both the education and NLP research communities. This work contributes to the ongoing dialogue on the potential uses of LLMs in educational settings.