An Empirical Evaluation of LLM-Based Approaches for Code Vulnerability Detection: RAG, SFT, and Dual-Agent Systems
Bibliographic record
Abstract
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.015 | 0.047 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".