Diverse LLMs vs. Vulnerabilities: Who Detects and Fixes Them Better?

• URL: http://arxiv.org/abs/2512.12536v1
• Date: Sun, 14 Dec 2025 03:47:39 GMT
• Title: Diverse LLMs vs. Vulnerabilities: Who Detects and Fixes Them Better?
• Authors: Arastoo Zibaeirad, Marco Vieira,
• Abstract summary: DVDR-LLM is an ensemble framework that combines outputs from diverse large language models.<n>Our evaluation reveals that DVDR-LLM 10-12% higher detection accuracy compared to the average performance of individual models.
• Score: 1.0026496861838445
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) are increasingly being studied for Software Vulnerability Detection (SVD) and Repair (SVR). Individual LLMs have demonstrated code understanding abilities, but they frequently struggle when identifying complex vulnerabilities and generating fixes. This study presents DVDR-LLM, an ensemble framework that combines outputs from diverse LLMs to determine whether aggregating multiple models reduces error rates. Our evaluation reveals that DVDR-LLM achieves 10-12% higher detection accuracy compared to the average performance of individual models, with benefits increasing as code complexity grows. For multi-file vulnerabilities, the ensemble approach demonstrates significant improvements in recall (+18%) and F1 score (+11.8%) over individual models. However, the approach raises measurable trade-offs: reducing false positives in verification tasks while simultaneously increasing false negatives in detection tasks, requiring careful decision on the required level of agreement among the LLMs (threshold) for increased performance across different security contexts. Artifact: https://github.com/Erroristotle/DVDR_LLM

Related papers

• Learning to Trust the Crowd: A Multi-Model Consensus Reasoning Engine for Large Language Models [0.0]
  Large language models (LLMs) achieve strong aver- age performance yet remain unreliable at the instance level.<n>We introduce a Multi-Model Consensus Reasoning Engine that treats the set of LLM outputs as input to a supervised meta-learner.<n>The system maps natural language responses into structured features using semantic embeddings, pairwise similarity and clustering statistics, lexical and structural cues, reasoning-quality scores, confidence estimates, and model-specific priors.
  arXiv  Detail & Related papers  (2026-01-12T06:27:06Z)
• Large Language Model based Smart Contract Auditing with LLMBugScanner [16.70822025530469]
  Smart contract auditing presents several challenges for large language models (LLM)<n>No single model performs consistently well across all vulnerability types or contract structures.<n>LLMBugScanner combines domain knowledge adaptation with ensemble reasoning to improve robustness and generalization.
  arXiv  Detail & Related papers  (2025-11-29T19:13:44Z)
• Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads [104.9566359759396]
  We propose a lightweight alternative for step-level reasoning verification based on data-driven uncertainty scores.<n>Our findings suggest that the internal states of LLMs encode their uncertainty and can serve as reliable signals for reasoning verification.
  arXiv  Detail & Related papers  (2025-11-09T03:38:29Z)
• DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models [60.713908578319256]
  We propose Direct Discrepancy Learning (DDL) to optimize the detector with task-oriented knowledge.<n>Built upon this, we introduce DetectAnyLLM, a unified detection framework that achieves state-of-the-art MGTD performance.<n>MIRAGE samples human-written texts from 10 corpora across 5 text-domains, which are then re-generated or revised using 17 cutting-edge LLMs.
  arXiv  Detail & Related papers  (2025-09-15T10:59:57Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• 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)
• Reasoning with LLMs for Zero-Shot Vulnerability Detection [0.9208007322096533]
  We present textbfVulnSage, a comprehensive evaluation framework and a curated dataset from diverse, large-scale open-source system software projects.<n>The framework supports multi-granular analysis across function, file, and inter-function levels.<n>It employs four diverse zero-shot prompt strategies: Baseline, Chain-of-context, Think, and Think & verify.
  arXiv  Detail & Related papers  (2025-03-22T23:59:17Z)
• SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models [74.40683913645731]
  Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications.<n>Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth.<n>Analysis of these prompt scores reveals VLM biases and AND''/OR' signal ambiguities, notably that maximum scores are surprisingly suboptimal compared to second-highest scores.
  arXiv  Detail & Related papers  (2025-02-24T07:15:05Z)
• Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents [5.993182776695028]
  Large language models (LLMs) are increasingly integrated into autonomous systems, giving rise to a new class of software known as Agentware.<n>This paper introduces the concept of cognitive observability - the ability to recover and inspect the implicit reasoning behind agent decisions.<n>We present Watson, a framework for observing the reasoning processes of fast-thinking LLM agents without altering their behavior.
  arXiv  Detail & Related papers  (2024-11-05T19:13:22Z)
• Fake Alignment: Are LLMs Really Aligned Well? [91.26543768665778]
  This study investigates the substantial discrepancy in performance between multiple-choice questions and open-ended questions. Inspired by research on jailbreak attack patterns, we argue this is caused by mismatched generalization.
  arXiv  Detail & Related papers  (2023-11-10T08:01:23Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)

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.