{"data":{"id":"f02f169a-d3c4-4182-94ae-3313fc8cbae6","title":"Narratives Mislead: An Empirical Study of How LLMs Misjudge CVSS Severity in Bug Bounty Reports","summary":"This study tests whether LLMs misjudge CVSS severity from narrative bug bounty reports, using 240 Huntr reports with vendor-validated CVSS vectors and eight models under four prompting strategies and fine-tuning. The best prompting configuration reaches only 49.58% level accuracy, and fine-tuning a 7B model raises this to at most 56.25%. Errors are directional: models overestimate far more often than they underestimate, and they almost never recognize low-severity vulnerabilities.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.24623v1","publishedAt":"2026-10-17T10:56:33.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["LLMs","HackerOne","Huntr"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-17T10:56:33.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":null,"llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}