基于 HooK 层的连续批次模型编辑
Consecutive Batch Model Editing with HooK Layers
AI总结:
针对现有模型编辑方法无法兼顾连续与批次编辑及内存需求过高的问题,提出仅需少量固定内存存储 hook 层的 CoachHooK 方法,在单轮和连续批次编辑场景中表现优异且稳定性强。
摘要:
由于典型的重新训练范式在时间和资源消耗上令人难以接受,研究人员正转向模型编辑,以寻找一种有效的方式,支持在连续和批次场景下直接编辑模型行为。尽管有这些实际期望,现有的模型编辑方法仍无法全部实现。此外,此类顺序模型编辑方法的内存需求往往过高,通常需要随时间不断增长的外部存储器。为了应对这些挑战,我们提出了 CoachHooK,一种同时支持顺序和批次编辑的模型编辑方法。CoachHooK 对内存友好,因为它只需少量内存来存储几个 hook 层,其大小随时间保持不变。实验结果表明,在单轮和连续批次编辑场景下,我们的方法优于其他支持批次的模型编辑方法。我们对 CoachHooK 进行了广泛分析,验证了该方法在多个连续步骤上的稳定性。
英文摘要:
As the typical retraining paradigm is unacceptably time- and resource-consuming, researchers are turning to model editing to find an effective way that supports both consecutive and batch scenarios 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 sequential model editing approaches tend to be prohibitive, frequently necessitating an external memory that grows incrementally over time. To cope with these challenges, we propose CoachHooK, a model editing method that simultaneously supports sequential and batch editing. CoachHooK is memory-friendly as it only needs a small amount of it to store several hook layers whose size remains unchanged over time. 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 CoachHooK have been conducted to verify the stability of our method over a number of consecutive steps.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。