@inproceedings{zhao-etal-2024-sapt,
title = "{SAPT}: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models",
author = "Zhao, Weixiang and
Wang, Shilong and
Hu, Yulin and
Zhao, Yanyan and
Qin, Bing and
Zhang, Xuanyu and
Yang, Qing and
Xu, Dongliang and
Che, Wanxiang",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.625",
pages = "11641--11661",
abstract = "The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the selection module to pick out the corresponding one for the testing input, aiming at handling the challenges of catastrophic forgetting and knowledge transfer in CL. However, these methods tend to address only one of the challenges, ignoring the potential of aligning the two modules to effectively address catastrophic forgetting and knowledge transfer simultaneously. To this end, we propose a novel Shared Attention Framework (SAPT), to align the PET learning and selection via the Shared Attentive Learning {\&} Selection module. Extensive Experiments on two CL benchmarks demonstrate the superiority of SAPT. Moreover, SAPT consistently demonstrates its superiority when we scale it to different model sizes (from 770M to 13B), different model architectures (T5 and LLaMA-2) and unseen tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2024-sapt">
<titleInfo>
<title>SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weixiang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shilong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulin</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanyan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongliang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the selection module to pick out the corresponding one for the testing input, aiming at handling the challenges of catastrophic forgetting and knowledge transfer in CL. However, these methods tend to address only one of the challenges, ignoring the potential of aligning the two modules to effectively address catastrophic forgetting and knowledge transfer simultaneously. To this end, we propose a novel Shared Attention Framework (SAPT), to align the PET learning and selection via the Shared Attentive Learning & Selection module. Extensive Experiments on two CL benchmarks demonstrate the superiority of SAPT. Moreover, SAPT consistently demonstrates its superiority when we scale it to different model sizes (from 770M to 13B), different model architectures (T5 and LLaMA-2) and unseen tasks.</abstract>
<identifier type="citekey">zhao-etal-2024-sapt</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.625</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>11641</start>
<end>11661</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models
%A Zhao, Weixiang
%A Wang, Shilong
%A Hu, Yulin
%A Zhao, Yanyan
%A Qin, Bing
%A Zhang, Xuanyu
%A Yang, Qing
%A Xu, Dongliang
%A Che, Wanxiang
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zhao-etal-2024-sapt
%X The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the selection module to pick out the corresponding one for the testing input, aiming at handling the challenges of catastrophic forgetting and knowledge transfer in CL. However, these methods tend to address only one of the challenges, ignoring the potential of aligning the two modules to effectively address catastrophic forgetting and knowledge transfer simultaneously. To this end, we propose a novel Shared Attention Framework (SAPT), to align the PET learning and selection via the Shared Attentive Learning & Selection module. Extensive Experiments on two CL benchmarks demonstrate the superiority of SAPT. Moreover, SAPT consistently demonstrates its superiority when we scale it to different model sizes (from 770M to 13B), different model architectures (T5 and LLaMA-2) and unseen tasks.
%U https://aclanthology.org/2024.acl-long.625
%P 11641-11661
Markdown (Informal)
[SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models](https://aclanthology.org/2024.acl-long.625) (Zhao et al., ACL 2024)
ACL
- Weixiang Zhao, Shilong Wang, Yulin Hu, Yanyan Zhao, Bing Qin, Xuanyu Zhang, Qing Yang, Dongliang Xu, and Wanxiang Che. 2024. SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11641–11661, Bangkok, Thailand. Association for Computational Linguistics.