{"data":{"id":"7b277d65-3838-4d12-99cb-f343e44c62b1","title":"Reasoning-Token Spikes Under Prompted Untruthful Responses in Large Language Models","summary":"Researchers tested whether the number of reasoning tokens a model generates can signal untruthful behavior, without reading the reasoning content. Three reasoning-capable LLMs answered 210 multiple-choice questions under system prompts instructing them to answer truthfully, falsely, or without regard for truth. Truth-directed responses produced fewer reasoning tokens than both lie-directed and truth-indifferent responses across all three models, and untruthful instructions increased the likelihood of reasoning at all in one model. The authors present this as a proof of concept for a content-independent black-box signal, not yet a detector of spontaneous deception.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.10405v2","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":0.9,"researchCategory":"preprint","atlasIds":null}}