Analyzing LLM Usage in an Advanced Computing Class in India

This paper investigates the usage patterns of undergraduate and graduate students when engaging with LLMs to tackle programming assignments in the context of advanced computing courses. Existing work predominantly focuses on the influence of LLMs in introductory programming contexts. Additionally, there is a scarcity of studies analyzing actual conversations between students and LLMs. Our study provides a comprehensive quantitative and qualitative analysis of raw interactions between students and LLMs within an advanced computing course (Distributed Systems) at an Indian University. We further complement this by conducting student interviews to gain deeper insights into their usage patterns. Our study shows that students make use of LLMs in various ways: generating code or debugging code by identifying and fixing errors. They also copy and paste assignment descriptions into LLM interfaces for specific solutions, ask conceptual questions about complex programming ideas or theoretical concepts, and generate test cases to check code functionality and robustness. Our analysis includes over 4,000 prompts from 411 students and conducting interviews with 10 students. Our analysis shows that LLMs excel at generating boilerplate code and assisting in debugging, while students handle the integration of components and system troubleshooting. This aligns with the learning objectives of advanced computing courses, which are oriented towards teaching students how to build systems and troubleshoot, with less emphasis on generating code from scratch. Therefore, LLM tools can be leveraged to increase student productivity, as shown by the data we collected. This study contributes to the ongoing discussion on LLM use in education, advocating for their usefulness in advanced computing courses to complement higher-level learning and productivity.