Consecutive batch model editing with HooK layers

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...

Full description

Saved in:
Bibliographic Details
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:
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
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10679
record_format dspace
spelling sg-smu-ink.sis_research-106792024-11-28T09:13:55Z Consecutive batch model editing with HooK layers LI, Shuaiyi DENG, Yang CAI, Deng LU, Hongyuan CHEN, Liang LAM, Wai 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. 2024-11-01T07:00:00Z text application/pdf 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 http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Retraining paradigm Model editing Sequential and batch editing Artificial Intelligence and Robotics
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Retraining paradigm
Model editing
Sequential and batch editing
Artificial Intelligence and Robotics
spellingShingle Retraining paradigm
Model editing
Sequential and batch editing
Artificial Intelligence and Robotics
LI, Shuaiyi
DENG, Yang
CAI, Deng
LU, Hongyuan
CHEN, Liang
LAM, Wai
Consecutive batch model editing with HooK layers
description 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.
format text
author LI, Shuaiyi
DENG, Yang
CAI, Deng
LU, Hongyuan
CHEN, Liang
LAM, Wai
author_facet LI, Shuaiyi
DENG, Yang
CAI, Deng
LU, Hongyuan
CHEN, Liang
LAM, Wai
author_sort LI, Shuaiyi
title Consecutive batch model editing with HooK layers
title_short Consecutive batch model editing with HooK layers
title_full Consecutive batch model editing with HooK layers
title_fullStr Consecutive batch model editing with HooK layers
title_full_unstemmed Consecutive batch model editing with HooK layers
title_sort consecutive batch model editing with hook layers
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url 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
_version_ 1819113100670926848