@inproceedings{wu-etal-2024-advancing,
title = "Advancing Parameter Efficiency in Fine-tuning via Representation Editing",
author = "Wu, Muling and
Liu, Wenhao and
Wang, Xiaohua and
Li, Tianlong and
Lv, Changze and
Ling, Zixuan and
JianHao, Zhu and
Zhang, Cenyuan and
Zheng, Xiaoqing and
Huang, Xuanjing",
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.726",
doi = "10.18653/v1/2024.acl-long.726",
pages = "13445--13464",
abstract = "Parameter Efficient Fine-Tuning (PEFT) has gained significant attention for its ability to achieve competitive results while updating only a small subset of trainable parameters. Despite the promising performance of current PEFT methods, they present challenges in hyperparameter selection, such as determining the rank of LoRA or Adapter, or specifying the length of soft prompts. In addressing these challenges, we propose a novel approach to fine-tuning neural models, termed Representation EDiting (RED), which scales and biases the representation produced at each layer. RED substantially reduces the number of trainable parameters by a factor of 25,700 compared to full parameter fine-tuning, and by a factor of 32 compared to LoRA. Remarkably, RED achieves comparable or superior results to full parameter fine-tuning and other PEFT methods. Extensive experiments were conducted across models of varying architectures and scales, including RoBERTa, GPT-2, T5, and Llama-2, and the results demonstrate the efficiency and efficacy of RED, positioning it as a promising PEFT approach for large neural models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2024-advancing">
<titleInfo>
<title>Advancing Parameter Efficiency in Fine-tuning via Representation Editing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muling</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaohua</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianlong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changze</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixuan</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">JianHao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cenyuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqing</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</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>Parameter Efficient Fine-Tuning (PEFT) has gained significant attention for its ability to achieve competitive results while updating only a small subset of trainable parameters. Despite the promising performance of current PEFT methods, they present challenges in hyperparameter selection, such as determining the rank of LoRA or Adapter, or specifying the length of soft prompts. In addressing these challenges, we propose a novel approach to fine-tuning neural models, termed Representation EDiting (RED), which scales and biases the representation produced at each layer. RED substantially reduces the number of trainable parameters by a factor of 25,700 compared to full parameter fine-tuning, and by a factor of 32 compared to LoRA. Remarkably, RED achieves comparable or superior results to full parameter fine-tuning and other PEFT methods. Extensive experiments were conducted across models of varying architectures and scales, including RoBERTa, GPT-2, T5, and Llama-2, and the results demonstrate the efficiency and efficacy of RED, positioning it as a promising PEFT approach for large neural models.</abstract>
<identifier type="citekey">wu-etal-2024-advancing</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.726</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.726</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13445</start>
<end>13464</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Advancing Parameter Efficiency in Fine-tuning via Representation Editing
%A Wu, Muling
%A Liu, Wenhao
%A Wang, Xiaohua
%A Li, Tianlong
%A Lv, Changze
%A Ling, Zixuan
%A JianHao, Zhu
%A Zhang, Cenyuan
%A Zheng, Xiaoqing
%A Huang, Xuanjing
%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 wu-etal-2024-advancing
%X Parameter Efficient Fine-Tuning (PEFT) has gained significant attention for its ability to achieve competitive results while updating only a small subset of trainable parameters. Despite the promising performance of current PEFT methods, they present challenges in hyperparameter selection, such as determining the rank of LoRA or Adapter, or specifying the length of soft prompts. In addressing these challenges, we propose a novel approach to fine-tuning neural models, termed Representation EDiting (RED), which scales and biases the representation produced at each layer. RED substantially reduces the number of trainable parameters by a factor of 25,700 compared to full parameter fine-tuning, and by a factor of 32 compared to LoRA. Remarkably, RED achieves comparable or superior results to full parameter fine-tuning and other PEFT methods. Extensive experiments were conducted across models of varying architectures and scales, including RoBERTa, GPT-2, T5, and Llama-2, and the results demonstrate the efficiency and efficacy of RED, positioning it as a promising PEFT approach for large neural models.
%R 10.18653/v1/2024.acl-long.726
%U https://aclanthology.org/2024.acl-long.726
%U https://doi.org/10.18653/v1/2024.acl-long.726
%P 13445-13464
Markdown (Informal)
[Advancing Parameter Efficiency in Fine-tuning via Representation Editing](https://aclanthology.org/2024.acl-long.726) (Wu et al., ACL 2024)
ACL
- Muling Wu, Wenhao Liu, Xiaohua Wang, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, and Xuanjing Huang. 2024. Advancing Parameter Efficiency in Fine-tuning via Representation Editing. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13445–13464, Bangkok, Thailand. Association for Computational Linguistics.