@inproceedings{zhou-etal-2024-empirical,
title = "An Empirical Study on Parameter-Efficient Fine-Tuning for {M}ulti{M}odal Large Language Models",
author = "Zhou, Xiongtao and
He, Jie and
Ke, Yuhua and
Zhu, Guangyao and
Gutierrez Basulto, Victor and
Pan, Jeff",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.598",
pages = "10057--10084",
abstract = "Multimodal Large Language Models (MLLMs) fine-tuned with multimodal instruction-following data have demonstrated formidable capabilities in multimodal tasks. However, fine-tuning all parameters of MLLMs has become challenging due to the rapid growth of the overall model{'}s parameters. To address this issue, we study Parameter-Efficient Fine-Tuning (PEFT) methods for MLLMs. We aim to identify effective methods for enhancing performance in scenarios where only a limited number of parameters are trained. This paper conducts empirical studies that employ four widely used PEFT methods to fine-tune the LLM component of open-source MLLMs. We present a comprehensive analysis that encompasses various aspects, including the impact of PEFT methods on various models, parameters and location of PEFT module, fine-tuning data scale, model stability based on PEFT method, MLLM{'}s generalization, and hallucination. We evaluated four PEFT methods on seven datasets from two different categories, unseen and seen datasets. Across all experiments, we show that the adapter is the best-performing PEFT method in various aspects. At the same time, fine-tuning the connector layers leads to improved performance in most MLLMs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2024-empirical">
<titleInfo>
<title>An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiongtao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhua</namePart>
<namePart type="family">Ke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangyao</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Gutierrez Basulto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeff</namePart>
<namePart type="family">Pan</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>Findings of the Association for Computational Linguistics ACL 2024</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 and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal Large Language Models (MLLMs) fine-tuned with multimodal instruction-following data have demonstrated formidable capabilities in multimodal tasks. However, fine-tuning all parameters of MLLMs has become challenging due to the rapid growth of the overall model’s parameters. To address this issue, we study Parameter-Efficient Fine-Tuning (PEFT) methods for MLLMs. We aim to identify effective methods for enhancing performance in scenarios where only a limited number of parameters are trained. This paper conducts empirical studies that employ four widely used PEFT methods to fine-tune the LLM component of open-source MLLMs. We present a comprehensive analysis that encompasses various aspects, including the impact of PEFT methods on various models, parameters and location of PEFT module, fine-tuning data scale, model stability based on PEFT method, MLLM’s generalization, and hallucination. We evaluated four PEFT methods on seven datasets from two different categories, unseen and seen datasets. Across all experiments, we show that the adapter is the best-performing PEFT method in various aspects. At the same time, fine-tuning the connector layers leads to improved performance in most MLLMs.</abstract>
<identifier type="citekey">zhou-etal-2024-empirical</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.598</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>10057</start>
<end>10084</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models
%A Zhou, Xiongtao
%A He, Jie
%A Ke, Yuhua
%A Zhu, Guangyao
%A Gutierrez Basulto, Victor
%A Pan, Jeff
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F zhou-etal-2024-empirical
%X Multimodal Large Language Models (MLLMs) fine-tuned with multimodal instruction-following data have demonstrated formidable capabilities in multimodal tasks. However, fine-tuning all parameters of MLLMs has become challenging due to the rapid growth of the overall model’s parameters. To address this issue, we study Parameter-Efficient Fine-Tuning (PEFT) methods for MLLMs. We aim to identify effective methods for enhancing performance in scenarios where only a limited number of parameters are trained. This paper conducts empirical studies that employ four widely used PEFT methods to fine-tune the LLM component of open-source MLLMs. We present a comprehensive analysis that encompasses various aspects, including the impact of PEFT methods on various models, parameters and location of PEFT module, fine-tuning data scale, model stability based on PEFT method, MLLM’s generalization, and hallucination. We evaluated four PEFT methods on seven datasets from two different categories, unseen and seen datasets. Across all experiments, we show that the adapter is the best-performing PEFT method in various aspects. At the same time, fine-tuning the connector layers leads to improved performance in most MLLMs.
%U https://aclanthology.org/2024.findings-acl.598
%P 10057-10084
Markdown (Informal)
[An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models](https://aclanthology.org/2024.findings-acl.598) (Zhou et al., Findings 2024)
ACL