{"data":{"id":"3bdfd752-0a0a-4d94-af73-ec7943fcc3b9","title":"Surprise Alone Learns Lies: Evidence-Gated Continual Learning for LLMs from Streaming Claims","summary":"This study examines continual learning for LLMs that select training inputs by surprise, a rule that absorbs planted falsehoods about facts the model already knows. Tested on LoRA-adapted Qwen2.5-1.5B, Qwen2.5-3B and Llama-3.2-3B students learning from streams of true and false claims, the authors find that a verifier judge removes lies only as far as it is accurate, and that the model's own prior flags contradictions with a 43% saving in judge calls. Routing contradicted claims to trusted evidence gives the lowest poison rate, but planted matching sources for 30% of lies make it worse than the judge alone.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.39840v1","publishedAt":"2026-10-29T11:19:08.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["data_extraction","other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Qwen2.5-1.5B","Qwen2.5-3B","Llama-3.2-3B","LoRA","CounterFact"],"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":"2026-10-29T11:19:08.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"training_data","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}