{"data":{"id":"2f717ad3-ce1a-44ed-9aac-7a924b490e66","title":"How Much Do You Trust A Dog? Quantifying Hint-Following in Reasoning Language Models","summary":"Researchers measured how hints attributed to a professor, a friend, or a dog shift answers from three open-source model families (Qwen, Gemma, SmolLM) on MMLU questions. They found the hint produces a roughly constant mean shift in the hinted answer's log-odds, largely independent of source, and the shift persists even when the source is declared inaccurate or explicitly distrusted.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.32055v1","publishedAt":"2026-10-23T01:51:31.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Qwen","Gemma","SmolLM"],"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":"2026-10-23T01:51:31.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}