Write a Blog >>

Background: Recent advancements in large language models have motivated the practical use of such models in code generation and program synthesis. However, little is known about the effects of such tools on code readability and visual attention in practice. Objective: In this paper, we focus on GitHub Copilot to address the issues of readability and visual inspection of model generated code. Readability and low complexity are vital aspects of good source code, and visual inspection of generated code is important in light of automation bias. Method: Through a human experiment (n=21) we compare model generated code to code written completely by human programmers. We use a combination of static code analysis and human evaluators to assess code readability, and we use eye tracking to assess the visual inspection of code. Results: Our results suggest that model generated code is comparable in complexity and readability to code written entirely by human programmers. At the same time, eye tracking data suggests, to a statistically significant level, that programmers direct less visual attention to model generated code. Conclusion: Our findings highlight that reading code is more important than ever, and programmers should beware of complacency and automation bias with model generated code.

Mon 10 Oct

Displayed time zone: Eastern Time (US & Canada) change

11:10 - 11:45
Paper Presentation Session 2: Readability Assessment[Workshop] AeSIR '22 at Online Workshop 3
Chair(s): Fernanda Madeiral Vrije Universiteit Amsterdam
How Readable is Model Generated Code? Examining Readability and Visual Inspection of GitHub CopilotVirtual
[Workshop] AeSIR '22
Naser Al Madi Colby College
Rank Learning-Based Code Readability Assessment with Siamese Neural NetworksVirtual
[Workshop] AeSIR '22
Live Q&A
Q&A and Open Discussion on Readability AssessmentVirtual
[Workshop] AeSIR '22
Naser Al Madi Colby College, Qing Mi