A Study on Developer Behaviors for Validating and Repairing LLM-Generated Code Using Eye Tracking and IDE Actions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tang, Ningzhi, Chen, Meng, Ning, Zheng, Bansal, Aakash, Huang, Yu, McMillan, Collin, Li, Toby Jia-Jun
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929358126448640
author Tang, Ningzhi
Chen, Meng
Ning, Zheng
Bansal, Aakash
Huang, Yu
McMillan, Collin
Li, Toby Jia-Jun
author_facet Tang, Ningzhi
Chen, Meng
Ning, Zheng
Bansal, Aakash
Huang, Yu
McMillan, Collin
Li, Toby Jia-Jun
contents The increasing use of large language model (LLM)-powered code generation tools, such as GitHub Copilot, is transforming software engineering practices. This paper investigates how developers validate and repair code generated by Copilot and examines the impact of code provenance awareness during these processes. We conducted a lab study with 28 participants, who were tasked with validating and repairing Copilot-generated code in three software projects. Participants were randomly divided into two groups: one informed about the provenance of LLM-generated code and the other not. We collected data on IDE interactions, eye-tracking, cognitive workload assessments, and conducted semi-structured interviews. Our results indicate that, without explicit information, developers often fail to identify the LLM origin of the code. Developers generally employ similar validation and repair strategies for LLM-generated code, but exhibit behaviors such as frequent switching between code and comments, different attentional focus, and a tendency to delete and rewrite code. Being aware of the code's provenance led to improved performance, increased search efforts, more frequent Copilot usage, and higher cognitive workload. These findings enhance our understanding of how developers interact with LLM-generated code and carry implications for designing tools that facilitate effective human-LLM collaboration in software development.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16081
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Study on Developer Behaviors for Validating and Repairing LLM-Generated Code Using Eye Tracking and IDE Actions
Tang, Ningzhi
Chen, Meng
Ning, Zheng
Bansal, Aakash
Huang, Yu
McMillan, Collin
Li, Toby Jia-Jun
Software Engineering
Human-Computer Interaction
The increasing use of large language model (LLM)-powered code generation tools, such as GitHub Copilot, is transforming software engineering practices. This paper investigates how developers validate and repair code generated by Copilot and examines the impact of code provenance awareness during these processes. We conducted a lab study with 28 participants, who were tasked with validating and repairing Copilot-generated code in three software projects. Participants were randomly divided into two groups: one informed about the provenance of LLM-generated code and the other not. We collected data on IDE interactions, eye-tracking, cognitive workload assessments, and conducted semi-structured interviews. Our results indicate that, without explicit information, developers often fail to identify the LLM origin of the code. Developers generally employ similar validation and repair strategies for LLM-generated code, but exhibit behaviors such as frequent switching between code and comments, different attentional focus, and a tendency to delete and rewrite code. Being aware of the code's provenance led to improved performance, increased search efforts, more frequent Copilot usage, and higher cognitive workload. These findings enhance our understanding of how developers interact with LLM-generated code and carry implications for designing tools that facilitate effective human-LLM collaboration in software development.
title A Study on Developer Behaviors for Validating and Repairing LLM-Generated Code Using Eye Tracking and IDE Actions
topic Software Engineering
Human-Computer Interaction
url https://arxiv.org/abs/2405.16081