cs.LGNov 15, 2026

Protecting Safety during Reasoning Training with Low-Rank Fisher Regularisation

Authors: Neel Rajani, Ivan Titov

Organizations: ILCC, University of Edinburgh · ILLC, University of Amsterdam

Abstract

Large language models are trained to have safety guardrails, but these can be compromised while fine-tuning for new capabilities, such as reasoning. One way to mitigate this degradation is to modify the fine-tuning objective to preserve safety behaviour, but doing so effectively and efficiently remains challenging. We revisit Elastic Weight Consolidation (EWC), which penalises parameter updates based on sensitivity estimates from the diagonal of the Fisher information matrix (FIM). While EWC provides some protection, the diagonal approximation ignores interactions between parameters. We address this limitation by exploiting recent findings that safety-relevant behaviour is located in a low-rank subspace within models. Our method, Subspace-Projected Elastic Weight Consolidation (SP-EWC), projects gradients onto this subspace to capture non-diagonal curvature efficiently. We investigate three different ways of identifying the safety subspace: through safety fine-tuning updates (LoRA), safety-related activations (ActSVD), and contrastive representations of safety and utility data (cPCA). We find that this choice substantially affects performance, with SP-EWC using cPCA comparing favourably against existing methods by better maintaining safety guardrails without introducing excessive over-refusal.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 4, 2026

Safe Context Switching for Agents in the Wild: Mitigating Subspace Interference via Orthogonal Adaptation

Most Large Language Models exhibit a fundamental tension between two sequential tasks, such as logical reasoning and safety alignment. The high-variance internal states required for sophisticated Chain-of-Thought (CoT) deduction can geometrically interfere with latent representations encoding safety constraints. We identify this phenomenon as Sequential Subspace Interference, showing that standard fine-tuning on logical tasks such as multi-step mathematics and code generation can result in a 23.3% interference penalty on alignment benchmarks, substantially weakening the model's safety priors. This Reasoning Drift is not adequately captured by current adaptation methods because gradients for logical tasks are rarely orthogonal to safety objectives. To address this issue, we propose AURA (Adaptive Unique Residual Allocation), a spectral regularization framework that enforces Spectral Independence between reasoning and safety. By explicitly estimating the null space of the alignment manifold and constraining reasoning updates to its orthogonal complement, AURA enables models to improve logical reasoning without compromising safety. Empirically, AURA recovers 23.0% of the lost performance while preserving greater than 0.98 cosine fidelity to the safe state, demonstrating that reasoning and alignment can be effectively decoupled through geometric regularization.
Feb 19, 2026

Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning

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.
May 28, 2026

CSULoRA: Closest Safe Update Low-Rank Adaptation

Low-rank adaptation has become a standard method for parameter-efficient fine-tuning of large language models, but even small amounts of unsafe or adversarial fine-tuning data can substantially weaken the safety behavior of aligned models. Existing safety-preserving LoRA methods often rely on hard interventions such as projection, pruning, thresholding, or additional training objectives. While these methods can suppress unsafe update directions, they may also remove task-relevant information or require extra tuning. We introduce CSULoRA, a post-hoc method for correcting trained LoRA adapters through closest safe update estimation. CSULoRA estimates a safety-aligned subspace from the weight displacement between a safety-aligned model and its corresponding base checkpoint. It then decomposes each LoRA update into fully aligned, partially aligned, and off-subspace components. Instead of discarding components outside the estimated safety subspace, CSULoRA solves a closed-form penalized minimum-change problem that preserves the fully aligned component while smoothly attenuating potentially unsafe directions according to their relative energy. In adversarial fine-tuning experiments, CSULoRA substantially reduces attack success rate while preserving most of the utility gains obtained from standard LoRA fine-tuning.