{"data":{"id":"abf40bc4-b7a6-4bba-9d94-689c0ac8b1de","title":"Reasoning-Token Spikes Under Prompted Untruthful Responding in Large Language Models","summary":"Researchers tested whether the number of reasoning tokens a model generates can signal untruthful behavior, without needing access to the reasoning content. Three reasoning-capable large language models answered 210 multiple-choice questions under system prompts to respond truthfully, falsely, or without regard for truth. Truth-directed responses used fewer reasoning tokens than both lie-directed and truth-indifferent responses across all three models. The authors present this as a proof-of-concept signal, not yet a detector of spontaneous deception.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.10405v1","publishedAt":"2026-10-07T16:53:11.000Z","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":"2026-10-07T16:53:11.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":"preprint","atlasIds":null}}