{"data":{"id":"c293a919-bcfb-4c09-8455-3ed4a20abb7a","title":"Efficiency at What Cost? Safety and Fairness in Parameter-Efficient Fine-Tuning of LLMs","summary":"This study tests whether benign parameter-efficient fine-tuning of LLMs affects safety and fairness. Across 235 conversational variants of four instruction-tuned families (Meta-Llama-3-8B, Qwen2.5-7B, Mistral-7B, Gemma-7B) using LoRA, IA3, Prompt-Tuning and P-Tuning, plus 96 coding-task models, benign PEFT produced alignment shifts. Adapter-based methods were generally safer, and Gemma showed the steepest safety decline.","solution":"The source directs practitioners to start from a well-aligned base model, favor adapter-based PEFT, and audit safety and fairness at the category level.","labels":["safety","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11658947","publishedAt":"2026-08-18T13:16:30.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Meta","Mistral","Google","HuggingFace"],"affectedVendorsRaw":["Meta-Llama-3-8B","Qwen2.5-7B","Mistral-7B","Gemma-7B","HuggingFace"],"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":"2026-08-18T13:16:30.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety","integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"peer_reviewed","atlasIds":null}}