@inproceedings{kim-kim-2024-tuning,
title = "{IT}-Tuning : Parameter Efficient Information Token Tuning for Language Model",
author = "Kim, Jungu and
Kim, Hyeoncheol",
editor = "Zhao, Chen and
Mosbach, Marius and
Atanasova, Pepa and
Goldfarb-Tarrent, Seraphina and
Hase, Peter and
Hosseini, Arian and
Elbayad, Maha and
Pezzelle, Sandro and
Mozes, Maximilian",
booktitle = "Proceedings of the 9th Workshop on Representation Learning for NLP (RepL4NLP-2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.repl4nlp-1.6",
pages = "58--68",
abstract = "Recently, language models have demonstrated exceptional performance compared to their predecessors. In this context, attention mechanisms and pre-training significantly contribute to the enhanced performance of modern language models. Additionally, a continuously increasing number of parameters plays a crucial role in these advancements . However, an increase in the number of parameters significantly increases the GPU memory and training time required during fine-tuning of language models, this makes fine-tuning infeasible in environments with limited computing resources. Furthermore, after fine-tuning, the storage space required for deployment increases proportionally with the number of tasks, making it challenging to deploy devices with limited storage capacities. In this study, we propose IT-Tuning, a Parameter Efficient Fine-Tuning method that introduces a new concept called information tokens to address these issues.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-kim-2024-tuning">
<titleInfo>
<title>IT-Tuning : Parameter Efficient Information Token Tuning for Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jungu</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyeoncheol</namePart>
<namePart type="family">Kim</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 9th Workshop on Representation Learning for NLP (RepL4NLP-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marius</namePart>
<namePart type="family">Mosbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seraphina</namePart>
<namePart type="family">Goldfarb-Tarrent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Hase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arian</namePart>
<namePart type="family">Hosseini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maha</namePart>
<namePart type="family">Elbayad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandro</namePart>
<namePart type="family">Pezzelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Mozes</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>Recently, language models have demonstrated exceptional performance compared to their predecessors. In this context, attention mechanisms and pre-training significantly contribute to the enhanced performance of modern language models. Additionally, a continuously increasing number of parameters plays a crucial role in these advancements . However, an increase in the number of parameters significantly increases the GPU memory and training time required during fine-tuning of language models, this makes fine-tuning infeasible in environments with limited computing resources. Furthermore, after fine-tuning, the storage space required for deployment increases proportionally with the number of tasks, making it challenging to deploy devices with limited storage capacities. In this study, we propose IT-Tuning, a Parameter Efficient Fine-Tuning method that introduces a new concept called information tokens to address these issues.</abstract>
<identifier type="citekey">kim-kim-2024-tuning</identifier>
<location>
<url>https://aclanthology.org/2024.repl4nlp-1.6</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>58</start>
<end>68</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IT-Tuning : Parameter Efficient Information Token Tuning for Language Model
%A Kim, Jungu
%A Kim, Hyeoncheol
%Y Zhao, Chen
%Y Mosbach, Marius
%Y Atanasova, Pepa
%Y Goldfarb-Tarrent, Seraphina
%Y Hase, Peter
%Y Hosseini, Arian
%Y Elbayad, Maha
%Y Pezzelle, Sandro
%Y Mozes, Maximilian
%S Proceedings of the 9th Workshop on Representation Learning for NLP (RepL4NLP-2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F kim-kim-2024-tuning
%X Recently, language models have demonstrated exceptional performance compared to their predecessors. In this context, attention mechanisms and pre-training significantly contribute to the enhanced performance of modern language models. Additionally, a continuously increasing number of parameters plays a crucial role in these advancements . However, an increase in the number of parameters significantly increases the GPU memory and training time required during fine-tuning of language models, this makes fine-tuning infeasible in environments with limited computing resources. Furthermore, after fine-tuning, the storage space required for deployment increases proportionally with the number of tasks, making it challenging to deploy devices with limited storage capacities. In this study, we propose IT-Tuning, a Parameter Efficient Fine-Tuning method that introduces a new concept called information tokens to address these issues.
%U https://aclanthology.org/2024.repl4nlp-1.6
%P 58-68
Markdown (Informal)
[IT-Tuning : Parameter Efficient Information Token Tuning for Language Model](https://aclanthology.org/2024.repl4nlp-1.6) (Kim & Kim, RepL4NLP-WS 2024)
ACL