← Back to archive day

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

Songping Peng, Zhiheng Zhang, Daojian Zeng, Lincheng Jiang, Xieping Gao

38

Recommendation Score

breakthrough🔴 AdvancedNLPLLM ReasoningAlignment & SafetyTheoryBest for researchers

Research context

Primary field

NLP

Language understanding, generation, extraction, and evaluation.

Topics

LLM Reasoning, Alignment & Safety

Paper type

Theory

Best for

Best for researchers

arXiv categories

cs.AIcs.AI

Why It Matters

Coupled weight-activation constraints prevent safety drift during LLM fine-tuning, offering a theoretically grounded defense—essential for deploying reliable, safe LLMs in production without unintended harmful behavior emergence.

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.

Published April 14, 2026
© 2026 A2A.pub — AI to Action. From papers to practice, daily.
Summaries are AI-assistedPrivacyTerms