{"data":{"id":"e2ee5767-6789-4d97-aedf-b79c23107eab","title":"Jev as an LLM Safety Guardrail: An Empirical Study of Input Filtering, Selective Output Review, and Over-Refusal","summary":"This empirical study evaluates Jev, a probabilistic decision model, as a safety guardrail for a Qwen2.5-1.5B-based LLM pipeline across 970 benchmark prompts. Input filtering cut harmful-prompt answers from 527/720 (73.2%) to 17/720 (2.4%), but raised benign-prompt refusals from 3/250 (1.2%) to 27/250 (10.8%). Tiered filtering with selective output review reduced benign refusals to 10/250 (4.0%) and harmful answers to 40/720 (5.6%), with 8.1% of prompts requiring output review.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://arxiv.org/abs/2611.08845v1","publishedAt":"2026-11-06T01:03:36.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Qwen2.5-1.5B"],"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":"2026-11-06T01:03:36.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"inference","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}