Code Readability in the Age of Large Language Models: An Industrial Case Study from Atlassian
This addresses the problem of code readability for software engineers using LLMs, but it is incremental as it applies existing readability concepts to a new context.
The study investigated code readability in the context of large language models (LLMs) through a survey and comparison of LLM-generated code with human-written code, finding that readability remains critical and that their LLM-generated code is comparable to human-written code.
Software engineers spend a significant amount of time reading code during the software development process, especially in the age of large language models (LLMs) that can automatically generate code. However, little is known about the readability of the LLM-generated code and whether it is still important from practitioners' perspectives in this new era. In this paper, we conduct a survey to explore the practitioners' perspectives on code readability in the age of LLMs and investigate the readability of our LLM-based software development agents framework, HULA, by comparing its generated code with human-written code in real-world scenarios. Overall, the findings underscore that (1) readability remains a critical aspect of software development; (2) the readability of our LLM-generated code is comparable to human-written code, fostering the establishment of appropriate trust and driving the broad adoption of our LLM-powered software development platform.