Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints

ACL ARR 2026 January Submission4487 Authors

Keywords: Safety Alignment, Fine-Tuning, Large Language Models

Abstract: Safety alignment in Large Language Models (LLMs) remains highly fragile during fine-tuning, where even benign adaptation can degrade pre-trained refusal behaviors and enable harmful responses. Existing defenses typically constrain either weights or activations in isolation, without considering their coupled effects on safety. In this paper, we first theoretically demonstrate that constraining either weights or activations alone is insufficient for safety preservation. To robustly preserve safety alignment, we propose Coupled Weight and Activation Constraints (CWAC), a novel approach that simultaneously enforces a precomputed safety subspace on weight updates and applies targeted regularization to safety-critical features identified by sparse autoencoders. Extensive experiments across four widely used LLMs and diverse downstream tasks show that CWAC consistently achieves the lowest harmful scores with minimal impact on fine-tuning accuracy, substantially outperforming strong baselines even under high harmful data ratios.

Paper Type: Long

Research Area: Safety and Alignment in LLMs

Research Area Keywords: safety and alignment, applications, fine-tuning, robustness

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English

Submission Number: 4487