{"data":{"id":"a6a1fbae-716e-4667-851e-8fbf260426dc","title":"Task Format as a Factor in Adaptation: A Controlled Comparison of LoRA and Full Fine-Tuning for Prompt-Safety Classification","summary":"This study compares LoRA with full fine-tuning for prompt-safety classification, using a matched 400M encoder-decoder pair (Ettin) across three task formats and up to 15 seeds per cell. At pre-specified learning rates, full fine-tuning leads LoRA by 2-3 pp, but on the encoder the gap closes when both learning rates are chosen by the same search. Trained models beat a prompted 8B in domain yet trail it by 8-23 pp on adversarial jailbreaks and flag 27-66% of benign but harmful-looking prompts as unsafe, versus 2-3% for the 8B.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.33813v1","publishedAt":"2026-10-24T17:24:54.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Ettin","LoRA"],"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":"2026-10-24T17:24:54.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}