# Reasoning with LLMs for Zero-Shot Vulnerability Detection

arXiv: https://arxiv.org/abs/2503.17885 · HTML: https://mlsanity.com/paper/2503.17885/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 17 of its 46 references that are in the map.
- First posted on arXiv 22 Mar 2025.

## 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, 17 of 17)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought](https://mlsanity.com/paper/2501.04682/) (2025)
- [IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities](https://mlsanity.com/paper/2405.17238/) (2024)
- [Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities](https://mlsanity.com/paper/2311.16169/) (2023)
- [How Far Have We Gone in Vulnerability Detection Using Large Language Models](https://mlsanity.com/paper/2311.12420/) (2023)
- [Comparison of Static Application Security Testing Tools and Large Language Models for Repo-level Vulnerability Detection](https://mlsanity.com/paper/2407.16235/) (2024)
- [VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models](https://mlsanity.com/paper/2406.07595/) (2024)
- [VulnLLMEval: A Framework for Evaluating Large Language Models in Software Vulnerability Detection and Patching](https://mlsanity.com/paper/2409.10756/) (2024)
- [A Comprehensive Survey on the Security of Smart Grid: Challenges, Mitigations, and Future Research Opportunities](https://mlsanity.com/paper/2407.07966/) (2024)
- [Cyber-Physical Systems Security: A Comprehensive Review of Anomaly Detection Techniques](https://mlsanity.com/paper/2502.13256/) (2025)
- [INVARLLM: LLM-assisted Physical Invariant Extraction for Cyber-Physical Systems Anomaly Detection](https://mlsanity.com/paper/2411.10918/) (2024)

## Built on by (most cited first, 7 of 7)

- [From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection](https://mlsanity.com/paper/2602.14012/) (2026)
- [Revisiting Pre-trained Language Models for Vulnerability Detection](https://mlsanity.com/paper/2507.16887/) (2025)
- [A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards](https://mlsanity.com/paper/2505.13766/) (2025)
- [Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection](https://mlsanity.com/paper/2605.18153/) (2026)
- [Diverse LLMs vs. Vulnerabilities: Who Detects and Fixes Them Better?](https://mlsanity.com/paper/2512.12536/) (2025)
- [VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection](https://mlsanity.com/paper/2602.10787/) (2026)
- [How Reasoning Shapes Social Bias in LLM-Generated Code?](https://mlsanity.com/paper/2608.06829/) (2026)

## Abstract (arXiv)

Automating software vulnerability detection (SVD) remains a critical challenge in an era of increasingly complex and interdependent software systems. Despite significant advances in Large Language Models (LLMs) for code analysis, prevailing evaluation methodologies often lack the context-aware robustness necessary to capture real-world intricacies and cross-component interactions. To address these limitations, we present VulnSage, a comprehensive evaluation framework and a dataset curated from diverse, large-scale open-source system software projects developed in C/C++. Unlike prior datasets, it leverages a heuristic noise pre-filtering approach combined with LLM-based reasoning to ensure a representative and minimally noisy spectrum of vulnerabilities. The framework supports multi-granular analysis across function, file, and inter-function levels and employs four diverse zero-shot prompt strategies: Baseline, Chain-of-Thought, Think, and Think & Verify. Through this evaluation, we uncover that structured reasoning prompts substantially improve LLM performance, with Think & Verify reducing ambiguous responses from 20.3% to 9.1% while increasing accuracy. We further demonstrate that code-specialized models consistently outperform general-purpose alternatives, with performance varying significantly across vulnerability types, revealing that no single approach universally excels across all security contexts. Link to dataset and codes: https://github.com/Erroristotle/VulnSage.git