Substance Beats Style: Why Beginning Students Fail to Code with LLMs

TL;DR

This study investigates why beginner students struggle to effectively prompt LLMs for coding tasks, finding that understanding content over style and information content is crucial for success.

Contribution

The paper provides empirical evidence that content quality outweighs prompt style and highlights key challenges students face in coding with LLMs.

Findings

Content content predicts success more than prompt style.

Students often get stuck on trivial prompt edits.

Technical vocabulary alone does not determine prompt failure.

Abstract

Although LLMs are increasing the productivity of professional programmers, existing work shows that beginners struggle to prompt LLMs to solve text-to-code tasks. Why is this the case? This paper explores two competing hypotheses about the cause of student-LLM miscommunication: (1) students simply lack the technical vocabulary needed to write good prompts, and (2) students do not understand the extent of information that LLMs need to solve code generation tasks. We study (1) with a causal intervention experiment on technical vocabulary and (2) by analyzing graphs that abstract how students edit prompts and the different failures that they encounter. We find that substance beats style: a poor grasp of technical vocabulary is merely correlated with prompt failure; that the information content of prompts predicts success; that students get stuck making trivial edits; and more. Our findings have implications for the use of LLMs in programming education, and for efforts to make computing more accessible with LLMs.