Using Chain-of-Thought and Self-Consistency prompts, some LLMs removed over half of SAST false positives on a benchmark while missing no genuine weaknesses, and ensembling three models removed about 79%.
An Empirical Assessment of Machine Learning Approaches for Triaging Reports of a Java Static Analysis Tool,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Towards Effective Complementary Security Analysis using Large Language Models
Using Chain-of-Thought and Self-Consistency prompts, some LLMs removed over half of SAST false positives on a benchmark while missing no genuine weaknesses, and ensembling three models removed about 79%.