{"data":{"id":"b9601a99-8763-4ed0-84dc-48592499cd46","title":"Enabling Scalable Evaluation of Unfair Patterns in Medical LLMs","summary":"Researchers present a generative method that uses knowledge graphs, medical ontologies and a base LLM to produce red-teaming evaluation cases for medical LLMs at scale. Each case flips a sensitive attribute, such as insurance status, to check whether the model's answer changes unfairly. The authors report that the generated cases are reliable and reveal bias patterns, and they publish a bias evaluation dataset on GitHub.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://doi.org/10.1145/3861001","publishedAt":"2026-11-03T00:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"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":"2026-11-03T00:00:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"peer_reviewed","atlasIds":null}}