Consecutive batch model editing with HooK layers

• Main Authors: LI, Shuaiyi, DENG, Yang, CAI, Deng, LU, Hongyuan, CHEN, Liang, LAM, Wai
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Retraining paradigm; Model editing; Sequential and batch editing; Artificial Intelligence and Robotics
• Online Access: https://ink.library.smu.edu.sg/sis_research/9679; https://ink.library.smu.edu.sg/context/sis_research/article/10679/viewcontent/2024.emnlp_main.765.pdf
• Institution: Singapore Management University

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.