Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mao, Zhenyu, Li, Jialong, Jin, Dongming, Li, Munan, Tei, Kenji
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.14274
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911880753184768
author Mao, Zhenyu
Li, Jialong
Jin, Dongming
Li, Munan
Tei, Kenji
author_facet Mao, Zhenyu
Li, Jialong
Jin, Dongming
Li, Munan
Tei, Kenji
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14274
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-role Consensus through LLMs Discussions for Vulnerability Detection
Mao, Zhenyu
Li, Jialong
Jin, Dongming
Li, Munan
Tei, Kenji
Software Engineering
Artificial Intelligence
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.
title Multi-role Consensus through LLMs Discussions for Vulnerability Detection
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2403.14274