IssueSpecter combines coverage analysis with LLM defect detection to generate prioritized, actionable issue reports, achieving 84.6% validity on manually reviewed issues from 13 Python projects and outperforming a coverage-driven baseline.
Leveraging large language models for python unit test
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLM-Guided Issue Generation from Uncovered Code Segments
IssueSpecter combines coverage analysis with LLM defect detection to generate prioritized, actionable issue reports, achieving 84.6% validity on manually reviewed issues from 13 Python projects and outperforming a coverage-driven baseline.