MétaCan
Menu
Back to cohort

An Empirical Evaluation of LLM-Based Approaches for Code Vulnerability Detection: RAG, SFT, and Dual-Agent Systems

2025· article· W7125598063 on OpenAlexaff
Md Hasan Saju, Maher Muhtadi, Akramul Azim

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicSoftware Engineering Research
Canadian institutionsOntario Tech University
Fundersnot available
KeywordsTransparency (behavior)Vulnerability (computing)AuditBaseline (sea)Domain (mathematical analysis)SoftwareTask (project management)The Internet

Abstract

fetched live from OpenAlex

The rapid advancement of Large Language Models (LLMs) presents new opportunities for automated software vulnerability detection, a crucial task in securing modern codebases. This paper presents a comparative study on the effectiveness of LLM-based techniques for detecting software vulnerabilities. The study evaluates three approaches, Retrieval-Augmented Generation (RAG), Supervised Fine-Tuning (SFT), and a Dual-Agent LLM framework, against a baseline LLM model. A curated dataset was compiled from Big-Vul [1] and real-world code repositories from GitHub, focusing on five critical Common Weakness Enumeration (CWE) categories: CWE-119, CWE399, CWE-264, CWE-20, and CWE-200. Our RAG approach, which integrated external domain knowledge from the internet and the MITRE CWE database, achieved the highest overall accuracy (0.86) and F1 score (0.85), highlighting the value of contextual augmentation. Our SFT approach, implemented using parameter-efficient QLoRA adapters, also demonstrated strong performance. Our Dual-Agent system, an architecture in which a secondary agent audits and refines the output of the first, showed promise in improving reasoning transparency and error mitigation, with reduced resource overhead. These results emphasize that incorporating a domain expertise mechanism significantly strengthens the practical applicability of LLMs in real-world vulnerability detection tasks.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.015
metaresearch head score (Gemma)0.047
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.015
Threshold uncertainty score0.078

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0150.047
Meta-epidemiology (narrow)0.0020.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0060.003
Science and technology studies0.0010.001
Scholarly communication0.0020.004
Open science0.0030.004
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0010.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.156
GPT teacher head0.388
Teacher spread0.232 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicSoftware Engineering ResearchFrench-language works237,207