Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning
Jyotin Goel, Souvik Maji, Pratik Mazumder · Feb 19, 2026 · Citations: 0
How to use this page
Low trustUse this as background context only. Do not make protocol decisions from this page alone.
Best use
Background context only
What to verify
Validate the evaluation procedure and quality controls in the full paper before operational use.
Evidence quality
Low
Derived from extracted protocol signals and abstract evidence.
Abstract
Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a trade-off between safety and utility. We introduce a training framework that adapts regularization in response to safety risk, enabling models to remain aligned throughout fine-tuning. To estimate safety risk at training time, we explore two distinct approaches: a judge-based Safety Critic that assigns high-level harm scores to training batches, and an activation-based risk predictor built with a lightweight classifier trained on intermediate model activations to estimate harmful intent. Each approach provides a risk signal that is used to constrain updates deemed higher risk to remain close to a safe reference policy, while lower-risk updates proceed with standard training. We empirically verify that harmful intent signals are predictable from pre-generation activations and that judge scores provide effective high-recall safety guidance. Across multiple model families and attack scenarios, adaptive regularization with either risk estimation approach consistently lowers attack success rate compared to standard fine-tuning, preserves downstream performance, and adds no inference-time cost. This work demonstrates a principled mechanism for maintaining safety without sacrificing utility.