SOURCE-LINKED INTELLIGENCE
Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
Fine-tuning large language models (LLMs) on downstream tasks often weakens their previously aligned safety behavior, creating an inherent trade-off between task adaptation and safety preservation. Existing approaches attempt to mitigate this issue by identifying safety-relevant neurons, layers, or update directions in the original parameter space. However, safety-related information is often distributed across many directions in this space, causing downstream updates to overwrite parameters that encode safety behavior. We propose WSR-Tune, a Weight Space Reparameterization-based fine-tuning fr
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-10-19T14:02:31.000Z
First collected: 2026-10-20T12:22:22.327Z. This is not the publication date.