arXiv:2606.26629 · v2
From Weights to Features: Sparse-Autoencoder-Guided Activation Regularization for Continual Learning in Large Language Models
摘要
Weight-protecting regularizers such as elastic weight consolidation (EWC) are a standard defense against catastrophic forgetting; however, in the sequential fine-tuning of large language models, they exhibit a stability-plasticity tradeoff that penalty tuning cannot resolve. We attribute this limitation in part to polysemanticity: because each weight participates in many unrelated concepts, a per-weight importance score has difficulty isolating the knowledge that requires protection. We instead regularize in activation space, using a pretrained sparse autoencoder (SAE) as a fixed dictionary of approximately monosemantic features. We formulate continual learning as constrained optimization over feature drift, with a stability constraint on the features to be preserved and a plasticity constraint on the features used by the current task, and we show that the resulting squared-hinge loss is a regularized Lagrangian relaxation of this problem, with EWC as a special case. A replay variant measures drift on 200 stored sequences per previous task, whereas a data-free variant stores only a 197 KB feature mask per task, versus 6.5 GB for EWC. On TRACE (Gemma-2 9B, Llama-3.1 8B) and MedCL (Gemma-2 9B), the replay variant matches or exceeds SAE-based feature distillation at approximately one third of its per-step cost, and the data-free variant attains the highest mean overall performance among methods that store no previous-task data and add no task-specific parameters. Task-relevant units are linearly separable in the SAE basis but not in the neuron basis (ROC-AUC of 0.87-0.88 versus 0.50), and weight-space protection constrains the features of other tasks nearly as strongly as those of the protected task.
作者备注:19 pages, 8 figures. Submitted to IEEE Transactions on Audio, Speech and Language Processing. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible