@inproceedings{guo-etal-2024-meta,
title = "Meta-Tuning {LLM}s to Leverage Lexical Knowledge for Generalizable Language Style Understanding",
author = "Guo, Ruohao and
Xu, Wei and
Ritter, Alan",
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.luhme-long.740/",
doi = "10.18653/v1/2024.acl-long.740",
pages = "13708--13731",
abstract = "Language style is often used by writers to convey their intentions, identities, and mastery of language. In this paper, we show that current large language models struggle to capture some language styles without fine-tuning. To address this challenge, we investigate whether LLMs can be meta-trained based on representative lexicons to recognize new styles they have not been fine-tuned on. Experiments on 13 established style classification tasks, as well as 63 novel tasks generated using LLMs, demonstrate that meta-training with style lexicons consistently improves zero-shot transfer across styles. We release the code and data at https://github.com/octaviaguo/Style-LLM."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2024-meta">
<titleInfo>
<title>Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruohao</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</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>Language style is often used by writers to convey their intentions, identities, and mastery of language. In this paper, we show that current large language models struggle to capture some language styles without fine-tuning. To address this challenge, we investigate whether LLMs can be meta-trained based on representative lexicons to recognize new styles they have not been fine-tuned on. Experiments on 13 established style classification tasks, as well as 63 novel tasks generated using LLMs, demonstrate that meta-training with style lexicons consistently improves zero-shot transfer across styles. We release the code and data at https://github.com/octaviaguo/Style-LLM.</abstract>
<identifier type="citekey">guo-etal-2024-meta</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.740</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-long.740/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13708</start>
<end>13731</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding
%A Guo, Ruohao
%A Xu, Wei
%A Ritter, Alan
%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 guo-etal-2024-meta
%X Language style is often used by writers to convey their intentions, identities, and mastery of language. In this paper, we show that current large language models struggle to capture some language styles without fine-tuning. To address this challenge, we investigate whether LLMs can be meta-trained based on representative lexicons to recognize new styles they have not been fine-tuned on. Experiments on 13 established style classification tasks, as well as 63 novel tasks generated using LLMs, demonstrate that meta-training with style lexicons consistently improves zero-shot transfer across styles. We release the code and data at https://github.com/octaviaguo/Style-LLM.
%R 10.18653/v1/2024.acl-long.740
%U https://aclanthology.org/2024.luhme-long.740/
%U https://doi.org/10.18653/v1/2024.acl-long.740
%P 13708-13731
Markdown (Informal)
[Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding](https://aclanthology.org/2024.luhme-long.740/) (Guo et al., ACL 2024)
ACL