Beyond Retention: Orchestrating Structural Safety and Plasticity in Continual Learning for LLMs

Continual learning in Large Language Models (LLMs) faces the critical challenge of balancing stability (retaining old knowledge) and plasticity (learning new tasks). While Experience Replay (ER) is a standard countermeasure against catastrophic forgetting, its impact across diverse capabilities remains underexplored. In this work, we uncover a critical dichotomy in ER's behavior: while it induces positive backward transfer on robust, unstructured tasks (e.g., boosting performance on previous NLP classification tasks through repeated rehearsal), it causes severe negative transfer on fragile, structured domains like code generation (e.g., a significant relative drop in coding accuracy). This reveals that ER trades structural integrity for broad consolidation. To address this dilemma, we propose Orthogonal Subspace Wake-up (OSW). OSW identifies essential parameter subspaces of previous tasks via a brief "wake-up" phase and enforces orthogonal updates for new tasks, providing a mathematically grounded "safety guarantee" for established knowledge structures. Empirical results across a diverse four-task sequence demonstrate that OSW uniquely succeeds in preserving fragile coding abilities where Replay fails, while simultaneously maintaining high plasticity for novel tasks. Our findings emphasize the necessity of evaluating structural safety alongside average retention in LLM continual learning.