{"data":{"id":"4c385016-330e-4daa-9720-389e36a6000d","title":"CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty","summary":"CATCH (Continuous Adversarial Training for Consistent Honesty) trains LLMs toward honest answers and away from dishonest ones while preserving capabilities, using only hundreds of targets built from self-reporting scenarios. The authors evaluate Llama-3.3-70B-Instruct and Qwen3-3.6-27B, reporting less dishonesty under pressure on MASK, more confessions in Among Us, and better discovery of hidden behaviours in AuditBench. CATCH matches state-of-the-art honesty activation steering and outperforms it on utility retention.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://arxiv.org/abs/2610.22292v1","publishedAt":"2026-10-15T17:43:47.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Llama-3.3-70B-Instruct","Qwen3-3.6-27B"],"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":"2026-10-15T17:43:47.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}