{"data":{"id":"93669b60-3279-46df-bfd5-073a171765f9","title":"ABench: Adversarily Benchmarking Large Language Models across Taxonomized Values","summary":"The authors introduce ABench, a handcrafted benchmark for testing LLM value alignment in Chinese, built on a hierarchical taxonomy of 158 value subcategories and 2,895 open-ended questions. The questions use role-playing and logical traps to test whether models keep their stances under adversarial induction, and the authors add a weighted automated evaluation framework. Across 16 mainstream LLMs, most models scored below 60 under these attacks, indicating significant vulnerabilities.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.27611v1","publishedAt":"2026-10-20T04:23:14.000Z","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":"2026-10-20T04:23:14.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}