A black-box LLM approach for fault localization in system-level test code that estimates execution traces from failure logs to rank potential faults with reduced inference cost.
Eric Wong, Vidroha Debroy, Ruizhi Gao, and Yihao Li
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
SPARK improves LLM-based test code fault localization by retrieving similar past faults and selectively annotating suspicious lines in new failing tests.
Debugging tools should present execution history in time order to support better hypothesis generation about program behavior.
citing papers explorer
-
Efficient Black-Box Fault Localization for System-Level Test Code Using Large Language Models
A black-box LLM approach for fault localization in system-level test code that estimates execution traces from failure logs to rank potential faults with reduced inference cost.
-
Similar Pattern Annotation via Retrieval Knowledge for LLM-Based Test Code Fault Localization
SPARK improves LLM-based test code fault localization by retrieving similar past faults and selectively annotating suspicious lines in new failing tests.
-
Tracers for debugging and program exploration
Debugging tools should present execution history in time order to support better hypothesis generation about program behavior.