{"data":{"id":"ca3012cc-59f7-4e20-bc41-3c34d15173c5","title":"Beyond Binary Labels: Diagnostic Evaluation of LLM Safety with Prompt-Level Rubrics","summary":"DiagSafe is a diagnostic framework for evaluating LLM safety that replaces binary safe or unsafe labels with prompt-level rubrics covering safety and usefulness. Tested on a bilingual English-Chinese benchmark built on an 84-label safety taxonomy, it reached 95.34% agreement with human annotations, versus 69%-87% for baselines, and found that leading LLMs differ markedly in unsafe rates and are particularly susceptible in Chinese and multi-turn contexts.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://arxiv.org/abs/2610.29225v1","publishedAt":"2026-10-21T05:33:50.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-10-21T05:33:50.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}