Multi-role Consensus through LLMs Discussions for Vulnerability Detection
This addresses the problem of limited perspectives in vulnerability detection for software quality assurance, offering an incremental improvement over single-role methods.
The paper tackles vulnerability detection in software by introducing a multi-role approach using LLMs to simulate discussions among different roles like developers and testers, achieving a 13.48% increase in precision, 18.25% in recall, and 16.13% in F1 score.
Recent advancements in large language models (LLMs) have highlighted the potential for vulnerability detection, a crucial component of software quality assurance. Despite this progress, most studies have been limited to the perspective of a single role, usually testers, lacking diverse viewpoints from different roles in a typical software development life-cycle, including both developers and testers. To this end, this paper introduces a multi-role approach to employ LLMs to act as different roles simulating a real-life code review process and engaging in discussions toward a consensus on the existence and classification of vulnerabilities in the code. Preliminary evaluation of this approach indicates a 13.48% increase in the precision rate, an 18.25% increase in the recall rate, and a 16.13% increase in the F1 score.