Parameter Scale Impact on False Positives in Code Vulnerability Detection Benchmarks

This report synthesises findings from 10 peer-reviewed papers addressing the following research question: How does increasing parameter scale from 7B to 33B impact false positive rates in code vulnerability detection benchmarks like Big-Vul. While automated vulnerability detection techniques have made promising progress in detecting security vulnerabilities, their scalability and applicability remain challenging. The remarkable performance of Large Language Models (LLMs), such as GPT-4 and CodeLlama, on code-related. 8 claims were extracted from source literature; 8 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does increasing parameter scale from 7B to 33B impact false positive rates in code vulnerability detection benchmarks like Big-Vul?

Autonomous literature synthesis. Automated review score: 9.0/10. Full text and citation available at Assignee Research.