Understanding Help-Seeking Behavior of Students Using LLMs vs. Web Search for Writing SQL Queries

TL;DR

This study compares how students use web search and large language models like ChatGPT for writing SQL queries, revealing differences in interaction patterns, perceived mental demand, and query quality, with implications for programming education.

Contribution

It provides the first experimental comparison of web search versus LLMs in SQL query learning, highlighting differences in interaction and perceived effort.

Findings

Instructor-tuned LLMs require more interactions than ChatGPT and web search.

No significant difference in final query quality across conditions.

Students using instructor-tuned LLMs report lower mental demand.

Abstract

Growth in the use of large language models (LLMs) in programming education is altering how students write SQL queries. Traditionally, students relied heavily on web search for coding assistance, but this has shifted with the adoption of LLMs like ChatGPT. However, the comparative process and outcomes of using web search versus LLMs for coding help remain underexplored. To address this, we conducted a randomized interview study in a database classroom to compare web search and LLMs, including a publicly available LLM (ChatGPT) and an instructor-tuned LLM, for writing SQL queries. Our findings indicate that using an instructor-tuned LLM required significantly more interactions than both ChatGPT and web search, but resulted in a similar number of edits to the final SQL query. No significant differences were found in the quality of the final SQL queries between conditions, although the LLM conditions directionally showed higher query quality. Furthermore, students using instructor-tuned LLM reported a lower mental demand. These results have implications for learning and productivity in programming education.