LLM4PFA combines iterative LLM-based constraint extraction with Z3 solving to reduce false positives in static analysis, achieving 72-96% false positive reduction and 93% recall on a new benchmark.
https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo Gpt-4-turbo
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
-
Minimizing False Positives in Static Bug Detection via LLM-Enhanced Path Feasibility Analysis
LLM4PFA combines iterative LLM-based constraint extraction with Z3 solving to reduce false positives in static analysis, achieving 72-96% false positive reduction and 93% recall on a new benchmark.