An empirical study of four LLMs for statement-level Java fault localization finds Gemini-2.5-Flash most accurate, bug-report context strongly helpful, and few-shot/CoT gains inconsistent.
Title resolution pending
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Large Language Models for Fault Localization: An Empirical Study
An empirical study of four LLMs for statement-level Java fault localization finds Gemini-2.5-Flash most accurate, bug-report context strongly helpful, and few-shot/CoT gains inconsistent.