# VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection

arXiv: https://arxiv.org/abs/2602.10787 · HTML: https://mlsanity.com/paper/2602.10787/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 23 of its 73 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 23 of 23)

- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities](https://mlsanity.com/paper/2405.17238/) (2024)
- [Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG](https://mlsanity.com/paper/2406.11147/) (2024)
- [A Multi-Task Embedder For Retrieval Augmented LLMs](https://mlsanity.com/paper/2310.07554/) (2023)
- [LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning](https://mlsanity.com/paper/2401.16185/) (2024)
- [How Far Have We Gone in Vulnerability Detection Using Large Language Models](https://mlsanity.com/paper/2311.12420/) (2023)
- [Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs](https://mlsanity.com/paper/2406.14282/) (2024)
- [SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code](https://mlsanity.com/paper/2506.05692/) (2025)
- [To Err is Machine: Vulnerability Detection Challenges LLM Reasoning](https://mlsanity.com/paper/2403.17218/) (2024)
- [Comparison of Static Application Security Testing Tools and Large Language Models for Repo-level Vulnerability Detection](https://mlsanity.com/paper/2407.16235/) (2024)
- [Investigating Large Language Models for Code Vulnerability Detection: An Experimental Study](https://mlsanity.com/paper/2412.18260/) (2024)
- [LProtector: An LLM-driven Vulnerability Detection System](https://mlsanity.com/paper/2411.06493/) (2024)
- [Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning](https://mlsanity.com/paper/2503.01642/) (2025)
- [Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data](https://mlsanity.com/paper/2506.07390/) (2025)
- [Reasoning with LLMs for Zero-Shot Vulnerability Detection](https://mlsanity.com/paper/2503.17885/) (2025)
- [R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation](https://mlsanity.com/paper/2504.04699/) (2025)
- [VulDeePecker: A Deep Learning-Based System for Vulnerability Detection](https://mlsanity.com/paper/1801.01681/) (2018)
- [An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors](https://mlsanity.com/paper/2401.16310/) (2024)
- [Benchmarking Software Vulnerability Detection Techniques: A Survey](https://mlsanity.com/paper/2303.16362/) (2023)
- [Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models](https://mlsanity.com/paper/2504.04372/) (2025)
- [Code Vulnerability Detection: A Comparative Analysis of Emerging Large Language Models](https://mlsanity.com/paper/2409.10490/) (2024)
- [Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models](https://mlsanity.com/paper/2505.17460/) (2025)

## Abstract (arXiv)

Software vulnerability detection (SVD) is a critical challenge in modern systems. Large language models (LLMs) offer natural-language explanations alongside predictions, but most work focuses on binary evaluation, and explanations often lack semantic consistency with Common Weakness Enumeration (CWE) categories. We propose VulReaD, a knowledge-graph-guided approach for vulnerability reasoning and detection that moves beyond binary classification toward CWE-level reasoning. VulReaD leverages a security knowledge graph (KG) as a semantic backbone and uses a strong teacher LLM to generate CWE-consistent contrastive reasoning supervision, enabling student model training without manual annotations. Students are fine-tuned with Odds Ratio Preference Optimization (ORPO) to encourage taxonomy-aligned reasoning while suppressing unsupported explanations. Across three real-world datasets, VulReaD improves binary F1 by 8-10% and multi-class classification by 30% Macro-F1 and 18% Micro-F1 compared to state-of-the-art baselines. Results show that LLMs outperform deep learning baselines in binary detection and that KG-guided reasoning enhances CWE coverage and interpretability.