LLM-generated refactoring motivations agree with expert raters about 80% of the time, align with literature motivations in roughly half of cases, and correlate only weakly with software metrics.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
What Were You Thinking? An LLM-Driven Large-Scale Study of Refactoring Motivations in Open-Source Projects
LLM-generated refactoring motivations agree with expert raters about 80% of the time, align with literature motivations in roughly half of cases, and correlate only weakly with software metrics.