As the typical retraining paradigm is unacceptably time- and resource-consuming, researchers are turning to model editing in order to seek an effective, consecutive, and batch-supportive way to edit the model behavior directly. Despite all these practical expectations, existing model editing methods fail to realize all of them. Furthermore, the memory demands for such succession-supportive model editing approaches tend to be prohibitive, frequently necessitating an external memory that grows incrementally over time. To cope with these challenges, we propose COMEBA-HK, a model editing method that is both consecutive and batch-supportive. COMEBA-HK is memory-friendly as it only needs a small amount of it to store several hook layers with updated weights. Experimental results demonstrate the superiority of our method over other batch-supportive model editing methods under both single-round and consecutive batch editing scenarios. Extensive analyses of COMEBA-HK have been conducted to verify the stability of our method over 1) the number of consecutive steps and 2) the number of editing instance.

翻译：由于典型的重新训练范式在时间和资源上难以承受，研究人员正转向模型编辑，以寻求一种有效、连续且支持批量的方式来直接编辑模型行为。尽管存在这些实际需求，现有的模型编辑方法未能同时实现所有这些特性。此外，支持连续编辑的模型编辑方法对内存的需求往往过高，常常需要随时间增长的外部存储。为应对这些挑战，我们提出COMEBA-HK，一种既连续又支持批量的模型编辑方法。该方法内存友好，仅需少量存储空间来保存多个更新权重的钩子层。实验结果表明，在单轮及连续批量编辑场景下，我们的方法均优于其他支持批量的模型编辑方法。通过对COMEBA-HK的全面分析，我们验证了该方法在1)连续编辑步骤数和2)编辑实例数量上的稳定性。