Prompting the Priorities: A First Look at Evaluating LLMs for Vulnerability Triage and Prioritization

• URL: http://arxiv.org/abs/2510.18508v1
• Date: Tue, 21 Oct 2025 10:48:14 GMT
• Title: Prompting the Priorities: A First Look at Evaluating LLMs for Vulnerability Triage and Prioritization
• Authors: Osama Al Haddad, Muhammad Ikram, Ejaz Ahmed, Young Lee,
• Abstract summary: Security analysts face increasing pressure to triage large and complex vulnerability backlogs.<n>We evaluate four models across twelve prompting techniques to interpret semi-structured and unstructured vulnerability information.<n>We issue more than 165,000 queries to assess performance under prompting styles including one-shot, few-shot, and chain-of-thought.
• Score: 0.8388262599725365
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Security analysts face increasing pressure to triage large and complex vulnerability backlogs. Large Language Models (LLMs) offer a potential aid by automating parts of the interpretation process. We evaluate four models (ChatGPT, Claude, Gemini, and DeepSeek) across twelve prompting techniques to interpret semi-structured and unstructured vulnerability information. As a concrete use case, we test each model's ability to predict decision points in the Stakeholder-Specific Vulnerability Categorization (SSVC) framework: Exploitation, Automatable, Technical Impact, and Mission and Wellbeing. Using 384 real-world vulnerabilities from the VulZoo dataset, we issued more than 165,000 queries to assess performance under prompting styles including one-shot, few-shot, and chain-of-thought. We report F1 scores for each SSVC decision point and Cohen's kappa (weighted and unweighted) for the final SSVC decision outcomes. Gemini consistently ranked highest, leading on three of four decision points and yielding the most correct recommendations. Prompting with exemplars generally improved accuracy, although all models struggled on some decision points. Only DeepSeek achieved fair agreement under weighted metrics, and all models tended to over-predict risk. Overall, current LLMs do not replace expert judgment. However, specific LLM and prompt combinations show moderate effectiveness for targeted SSVC decisions. When applied with care, LLMs can support vulnerability prioritization workflows and help security teams respond more efficiently to emerging threats.

Related papers

• The Vulnerability of LLM Rankers to Prompt Injection Attacks [40.03039307576983]
  Large Language Models (LLMs) have emerged as powerful re-rankers.<n>Recent research has showed that simple prompt injections embedded within a candidate document can significantly alter an LLM's ranking decisions.
  arXiv  Detail & Related papers  (2026-02-18T06:19:08Z)
• From Description to Score: Can LLMs Quantify Vulnerabilities? [2.7554928070512843]
  This study investigates the potential of general-purpose large language models (LLMs) to automate the vulnerability scoring process.<n>Our analysis reveals that LLMs tend to misclassify many of the same CVEs, and ensemble-based meta-classifiers only marginally improve performance.
  arXiv  Detail & Related papers  (2025-12-07T10:47:00Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Curse of Knowledge: When Complex Evaluation Context Benefits yet Biases LLM Judges [72.3356133063925]
  The paradigm of large language models (LLMs) as judges has emerged as a scalable solution, yet prior work primarily focuses on simple settings.<n>Our in-depth analysis offers crucial insights for improving the accuracy and verifiability of evaluation signals.
  arXiv  Detail & Related papers  (2025-09-03T15:48:33Z)
• Think Broad, Act Narrow: CWE Identification with Multi-Agent Large Language Models [0.09208007322096533]
  Machine learning and large language models (LLMs) for vulnerability detection have received significant attention in recent years.<n>We propose a novel multi-agent LLM approach to address the challenges of identifying security weaknesses (CWEs)<n>In the PrimeVul dataset, Step 1 correctly identifies the appropriate CWE in 40.9% of the studied vulnerable functions.
  arXiv  Detail & Related papers  (2025-08-02T17:57:46Z)
• Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection [15.694744168599055]
  Existing vulnerability detection methods face two main issues.<n>They lack comprehensive coverage and high-quality explanations for preference learning.<n>Large language models (LLMs) often struggle with accurately interpreting specific concepts in smart contract security.
  arXiv  Detail & Related papers  (2025-06-23T02:24:07Z)
• VADER: A Human-Evaluated Benchmark for Vulnerability Assessment, Detection, Explanation, and Remediation [0.8087612190556891]
  VADER comprises 174 real-world software vulnerabilities, each carefully curated from GitHub and annotated by security experts.<n>For each vulnerability case, models are tasked with identifying the flaw, classifying it using Common Weaknession (CWE), explaining its underlying cause, proposing a patch, and formulating a test plan.<n>Using a one-shot prompting strategy, we benchmark six state-of-the-art LLMs (Claude 3.7 Sonnet, Gemini 2.5 Pro, GPT-4.1, GPT-4.5, Grok 3 Beta, and o3) on VADER.<n>Our results show that current state-of-the-
  arXiv  Detail & Related papers  (2025-05-26T01:20:44Z)
• Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask [30.819697001992154]
  Large Language Models are a promising tool for automated vulnerability detection.<n>Despite widespread adoption, a critical question remains: Are LLMs truly effective at detecting real-world vulnerabilities?<n>This paper challenges three widely held community beliefs: that LLMs are (i) unreliable, (ii) insensitive to code patches, and (iii) performance-plateaued across model scales.
  arXiv  Detail & Related papers  (2025-04-18T05:32:47Z)
• SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models [50.34706204154244]
  Acquiring reasoning capabilities catastrophically degrades inherited safety alignment.<n>Certain scenarios suffer 25 times higher attack rates.<n>Despite tight reasoning-answer safety coupling, MLRMs demonstrate nascent self-correction.
  arXiv  Detail & Related papers  (2025-04-09T06:53:23Z)
• SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI [58.29510889419971]
  Existing benchmarks for evaluating the security risks and capabilities of code-generating large language models (LLMs) face several key limitations.<n>We introduce a general and scalable benchmark construction framework that begins with manually validated, high-quality seed examples and expands them via targeted mutations.<n>Applying this framework to Python, C/C++, and Java, we build SeCodePLT, a dataset of more than 5.9k samples spanning 44 CWE-based risk categories and three security capabilities.
  arXiv  Detail & Related papers  (2024-10-14T21:17:22Z)
• SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal [64.9938658716425]
  SORRY-Bench is a proposed benchmark for evaluating large language models' (LLMs) ability to recognize and reject unsafe user requests.<n>First, existing methods often use coarse-grained taxonomy of unsafe topics, and are over-representing some fine-grained topics.<n>Second, linguistic characteristics and formatting of prompts are often overlooked, like different languages, dialects, and more -- which are only implicitly considered in many evaluations.
  arXiv  Detail & Related papers  (2024-06-20T17:56:07Z)
• ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models [65.79770974145983]
  ASSERT, Automated Safety Scenario Red Teaming, consists of three methods -- semantically aligned augmentation, target bootstrapping, and adversarial knowledge injection. We partition our prompts into four safety domains for a fine-grained analysis of how the domain affects model performance. We find statistically significant performance differences of up to 11% in absolute classification accuracy among semantically related scenarios and error rates of up to 19% absolute error in zero-shot adversarial settings.
  arXiv  Detail & Related papers  (2023-10-14T17:10:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.