@inproceedings{olariu-etal-2023-evaluating,
title = "Evaluating Parameter-Efficient Finetuning Approaches for Pre-trained Models on the Financial Domain",
author = "Olariu, Isabella and
Lothritz, Cedric and
Klein, Jacques and
Bissyand{\'e}, Tegawend{\'e} and
Guo, Siwen and
Haddadan, Shohreh",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.1035",
doi = "10.18653/v1/2023.findings-emnlp.1035",
pages = "15482--15491",
abstract = "Large-scale language models with millions, billions, or trillions of trainable parameters are becoming increasingly popular. However, they risk becoming rapidly over-parameterized and the adaptation cost of fully fine-tuning them increases significantly. Storing them becomes progressively impractical as it requires keeping a separate copy of all the fine-tuned weights for each task. By freezing all pre-trained weights during fine-tuning, parameter-efficient tuning approaches have become an appealing alternative to traditional fine-tuning. The performance of these approaches has been evaluated on common NLP tasks of the GLUE benchmark and shown to match full fine-tuning performance, however, their impact is less researched in domain-specific fields such as finance. This work compares the performance of a set of financial BERT-like models to their fully fine-tuned counterparts by leveraging different parameter-efficient tuning methods. We see that results are comparable to traditional fine-tuning while gaining in time and resource efficiency.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="olariu-etal-2023-evaluating">
<titleInfo>
<title>Evaluating Parameter-Efficient Finetuning Approaches for Pre-trained Models on the Financial Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabella</namePart>
<namePart type="family">Olariu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cedric</namePart>
<namePart type="family">Lothritz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacques</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tegawendé</namePart>
<namePart type="family">Bissyandé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siwen</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shohreh</namePart>
<namePart type="family">Haddadan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale language models with millions, billions, or trillions of trainable parameters are becoming increasingly popular. However, they risk becoming rapidly over-parameterized and the adaptation cost of fully fine-tuning them increases significantly. Storing them becomes progressively impractical as it requires keeping a separate copy of all the fine-tuned weights for each task. By freezing all pre-trained weights during fine-tuning, parameter-efficient tuning approaches have become an appealing alternative to traditional fine-tuning. The performance of these approaches has been evaluated on common NLP tasks of the GLUE benchmark and shown to match full fine-tuning performance, however, their impact is less researched in domain-specific fields such as finance. This work compares the performance of a set of financial BERT-like models to their fully fine-tuned counterparts by leveraging different parameter-efficient tuning methods. We see that results are comparable to traditional fine-tuning while gaining in time and resource efficiency.</abstract>
<identifier type="citekey">olariu-etal-2023-evaluating</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.1035</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.1035</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>15482</start>
<end>15491</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Parameter-Efficient Finetuning Approaches for Pre-trained Models on the Financial Domain
%A Olariu, Isabella
%A Lothritz, Cedric
%A Klein, Jacques
%A Bissyandé, Tegawendé
%A Guo, Siwen
%A Haddadan, Shohreh
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F olariu-etal-2023-evaluating
%X Large-scale language models with millions, billions, or trillions of trainable parameters are becoming increasingly popular. However, they risk becoming rapidly over-parameterized and the adaptation cost of fully fine-tuning them increases significantly. Storing them becomes progressively impractical as it requires keeping a separate copy of all the fine-tuned weights for each task. By freezing all pre-trained weights during fine-tuning, parameter-efficient tuning approaches have become an appealing alternative to traditional fine-tuning. The performance of these approaches has been evaluated on common NLP tasks of the GLUE benchmark and shown to match full fine-tuning performance, however, their impact is less researched in domain-specific fields such as finance. This work compares the performance of a set of financial BERT-like models to their fully fine-tuned counterparts by leveraging different parameter-efficient tuning methods. We see that results are comparable to traditional fine-tuning while gaining in time and resource efficiency.
%R 10.18653/v1/2023.findings-emnlp.1035
%U https://aclanthology.org/2023.findings-emnlp.1035
%U https://doi.org/10.18653/v1/2023.findings-emnlp.1035
%P 15482-15491
Markdown (Informal)
[Evaluating Parameter-Efficient Finetuning Approaches for Pre-trained Models on the Financial Domain](https://aclanthology.org/2023.findings-emnlp.1035) (Olariu et al., Findings 2023)
ACL