@inproceedings{dredze-etal-2024-academics,
title = "Academics Can Contribute to Domain-Specialized Language Models",
author = "Dredze, Mark and
Winata, Genta Indra and
Kambadur, Prabhanjan and
Wu, Shijie and
Irsoy, Ozan and
Lu, Steven and
Dabravolski, Vadim and
Rosenberg, David S and
Gehrmann, Sebastian",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.293/",
doi = "10.18653/v1/2024.emnlp-main.293",
pages = "5100--5110",
abstract = "Commercially available models dominate academic leaderboards. While impressive, this has concentrated research on creating and adapting general-purpose models to improve NLP leaderboard standings for large language models. However, leaderboards collect many individual tasks and general-purpose models often underperform in specialized domains; domain-specific or adapted models yield superior results. This focus on large general-purpose models excludes many academics and draws attention away from areas where they can make important contributions. We advocate for a renewed focus on developing and evaluating domain- and task-specific models, and highlight the unique role of academics in this endeavor."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dredze-etal-2024-academics">
<titleInfo>
<title>Academics Can Contribute to Domain-Specialized Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Dredze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prabhanjan</namePart>
<namePart type="family">Kambadur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijie</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ozan</namePart>
<namePart type="family">Irsoy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vadim</namePart>
<namePart type="family">Dabravolski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Rosenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Commercially available models dominate academic leaderboards. While impressive, this has concentrated research on creating and adapting general-purpose models to improve NLP leaderboard standings for large language models. However, leaderboards collect many individual tasks and general-purpose models often underperform in specialized domains; domain-specific or adapted models yield superior results. This focus on large general-purpose models excludes many academics and draws attention away from areas where they can make important contributions. We advocate for a renewed focus on developing and evaluating domain- and task-specific models, and highlight the unique role of academics in this endeavor.</abstract>
<identifier type="citekey">dredze-etal-2024-academics</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.293</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.293/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>5100</start>
<end>5110</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Academics Can Contribute to Domain-Specialized Language Models
%A Dredze, Mark
%A Winata, Genta Indra
%A Kambadur, Prabhanjan
%A Wu, Shijie
%A Irsoy, Ozan
%A Lu, Steven
%A Dabravolski, Vadim
%A Rosenberg, David S.
%A Gehrmann, Sebastian
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F dredze-etal-2024-academics
%X Commercially available models dominate academic leaderboards. While impressive, this has concentrated research on creating and adapting general-purpose models to improve NLP leaderboard standings for large language models. However, leaderboards collect many individual tasks and general-purpose models often underperform in specialized domains; domain-specific or adapted models yield superior results. This focus on large general-purpose models excludes many academics and draws attention away from areas where they can make important contributions. We advocate for a renewed focus on developing and evaluating domain- and task-specific models, and highlight the unique role of academics in this endeavor.
%R 10.18653/v1/2024.emnlp-main.293
%U https://aclanthology.org/2024.emnlp-main.293/
%U https://doi.org/10.18653/v1/2024.emnlp-main.293
%P 5100-5110
Markdown (Informal)
[Academics Can Contribute to Domain-Specialized Language Models](https://aclanthology.org/2024.emnlp-main.293/) (Dredze et al., EMNLP 2024)
ACL
- Mark Dredze, Genta Indra Winata, Prabhanjan Kambadur, Shijie Wu, Ozan Irsoy, Steven Lu, Vadim Dabravolski, David S Rosenberg, and Sebastian Gehrmann. 2024. Academics Can Contribute to Domain-Specialized Language Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 5100–5110, Miami, Florida, USA. Association for Computational Linguistics.