Using LLMs to Adjudicate Static-Analysis Alerts with Error Reduction Techniques

• URL: http://arxiv.org/abs/2607.09979v1
• Date: Fri, 10 Jul 2026 21:09:01 GMT
• Title: Using LLMs to Adjudicate Static-Analysis Alerts with Error Reduction Techniques
• Abstract summary: Large language models (LLMs) can adjudicate (classify as a real bug or a false alarm) static-analysis alerts.<n>We evaluate several LLMs on three test suites: Juliet, FormAI, and SV-COMP.<n>With mistake mitigation, they reach at least 98% recall and at least 94.8% specificity on every suite.
• Score: 4.007351600492542
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Static analysis is widely used for finding security weaknesses in source code before deployment, but it often produces far more alerts than analysts can review. We study how well large language models (LLMs) can adjudicate (classify as a real bug or a false alarm) static-analysis alerts. We use two mistake-mitigation methods: (1) a consistency check (CC) that runs the LLM multiple times and checks that the verdicts are consistent with each other, and (2) an LLM reasoning evaluation (LRE) step that runs the LLM multiple times and then asks the LLM to choose a verdict after evaluating the reasoning provided by each run. We evaluated several LLMs on three test suites: Juliet, FormAI, and SV-COMP. Across all three suites, the mid-tier reasoning LLMs that we tested (o4-mini, gpt-oss-120b, gpt-oss-20b) reach high recall (percent of real bugs that the tool correctly flags as needing repair / manual attention) and specificity (percent of actually false alerts that the tool correctly dismisses as false alarms). With mistake mitigation, they reach at least 98% recall and at least 94.8% specificity on every suite (with CC alone on Juliet and SV-COMP, and with LRE+CC on FormAI). We probe Juliet memorization and show that o4-mini can often reconstruct sanitized test cases' original identities, so we base our generalization claims primarily on FormAI, scored against our own unpublished manual adjudications. We also report results of using the LLM to synthesize a program that dynamically triggers the flaw as independent evidence; a validity check rejected every trigger driver aimed at a false alarm, so a valid trigger proved to be strong evidence of a real flaw.

Related papers

• LLM-as-a-Verifier: A General-Purpose Verification Framework [74.40111651545979]
  We introduce LLM-as-a-Verifier, a general-purpose verification framework.<n>It provides fine-grained feedback for agentic tasks without requiring additional training.<n>It achieves state-of-the-art performance on several benchmarks.
  arXiv  Detail & Related papers  (2026-07-06T17:59:35Z)
• The Hitchhiker's Guide to Program Analysis, Part III: Mostly Harmless LLMs [16.471977061248747]
  Evident is a bug analysis system that separates LLM assistance from program-behavior reasoning.<n>We evaluate Evident on 200 real Android kernel driver warnings from two existing static detectors.
  arXiv  Detail & Related papers  (2026-06-13T05:26:08Z)
• Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation [66.84286617519258]
  Large language models are transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis.<n>Such variation can introduce systematic biases and random errors, which propagate to downstream analyses and cause Type I (false positive), Type II (false negative), Type S (wrong sign), or Type M (exaggerated effect) errors.<n>We find that intentional LLM hacking is strikingly simple. By replicating 37 data annotation tasks from 21 published social science studies, we show that, with just a handful of prompt paraphrases, virtually anything can be presented as statistically significant.
  arXiv  Detail & Related papers  (2025-09-10T17:58:53Z)
• Repairing vulnerabilities without invisible hands. A differentiated replication study on LLMs [5.10123605644148]
  Automated Vulnerability Repair (AVR) is a fast-growing branch of program repair.<n>Recent studies show that large language models (LLMs) outperform traditional techniques.
  arXiv  Detail & Related papers  (2025-07-28T16:39:16Z)
• Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs [87.79350168490475]
  This work formally defines self-consistent errors and evaluates mainstream detection methods on them.<n>All four types of detection methods significantly struggle to detect self-consistent errors.<n>Motivated by the observation that self-consistent errors often differ across LLMs, we propose a simple but effective cross-model probe.
  arXiv  Detail & Related papers  (2025-05-23T09:18:56Z)
• Laurel: Unblocking Automated Verification with Large Language Models [2.6942525604796366]
  We propose Laurel, a tool that automatically generates assertions using large language models.<n>We evaluate our techniques on our new benchmark DafnyGym, a dataset of complex lemmas we extracted from three real-world Dafnys.
  arXiv  Detail & Related papers  (2024-05-27T03:26:01Z)
• Evaluating LLMs at Detecting Errors in LLM Responses [30.645694514606507]
  This work introduces ReaLMistake, the first error detection benchmark consisting of objective, realistic, and diverse errors made by LLMs. We use ReaLMistake to evaluate error detectors based on 12 Large Language Models.
  arXiv  Detail & Related papers  (2024-04-04T17:19:47Z)
• LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks [17.522223535347905]
  Large Language Models (LLMs) have been suggested for use in automated vulnerability repair, but benchmarks showing they can consistently identify security-related bugs are lacking. We develop SecLLMHolmes, a fully automated evaluation framework that performs the most detailed investigation to date on whether LLMs can reliably identify and reason about security-related bugs.
  arXiv  Detail & Related papers  (2023-12-19T20:19:43Z)
• 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)
• SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks [99.23352758320945]
  We propose SmoothLLM, the first algorithm designed to mitigate jailbreaking attacks on large language models (LLMs) Based on our finding that adversarially-generated prompts are brittle to character-level changes, our defense first randomly perturbs multiple copies of a given input prompt, and then aggregates the corresponding predictions to detect adversarial inputs.
  arXiv  Detail & Related papers  (2023-10-05T17:01:53Z)
• SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning [55.76083560152823]
  SelfCheck is a general-purpose zero-shot verification schema for recognizing errors in step-by-step reasoning. We test SelfCheck on three datasets (GSM8K, MathQA, and MATH) and find that it successfully recognizes errors and, in turn, increases final answer accuracies.
  arXiv  Detail & Related papers  (2023-08-01T10:31:36Z)
• Large Language Models are Better Reasoners with Self-Verification [48.534270563880845]
  Large language models (LLMs) have shown strong reasoning ability in several natural language processing tasks. LLMs with chain of thought (CoT) prompting require multi-step prompting and multi-token prediction, which is highly sensitive to individual mistakes. We propose and prove that LLMs also have similar self-verification abilities.
  arXiv  Detail & Related papers  (2022-12-19T15:51:52Z)

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.