When Privacy Hurts Mergeability: Geometry-Aware Model Merging under Differential Privacy

The paper investigates how differential privacy (DP) affects the ability to merge independently fine‑tuned task models into a single multi‑task model. It identifies two geometric challenges—local sharpness and reference drift—that hinder mergeability of private models. To address these, the authors propose DP‑Merging, a framework that uses a sharpness‑aware objective and a reference‑based alignment regularizer to improve mergeability while maintaining DP guarantees.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• fine-tuning
• safety