SafeTune puts four safety-drift fixes behind one audit workflow
Teams fine-tuning large language models can use SafeTune to audit safety drift and compare repair methods in one source-available library, instead of stitching together incompatible implementations. A configuration-driven workflow covers weight recovery, safety-constrained fine-tuning, gradient-based unlearning, and inference-time steering, while keeping each method’s required inputs and intervention point distinct. The paper demonstrates the workflow with controlled comparisons and finance and medical deployment case studies.