@inproceedings{doi-etal-2024-topic,
title = "Topic Modeling for Short Texts with Large Language Models",
author = "Doi, Tomoki and
Isonuma, Masaru and
Yanaka, Hitomi",
editor = "Fu, Xiyan and
Fleisig, Eve",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-srw.3",
pages = "21--33",
abstract = "As conventional topic models rely on word co-occurrence to infer latent topics, topic modeling for short texts has been a long-standing challenge. Large Language Models (LLMs) can potentially overcome this challenge by contextually learning the meanings of words via pretraining. In this paper, we study two approaches to using LLMs for topic modeling: parallel prompting and sequential prompting. Input length limitations prevent LLMs from processing many texts at once. However, an arbitrary number of texts can be handled by LLMs by splitting the texts into smaller subsets and processing them in parallel or sequentially. Our experimental results demonstrate that our methods can identify more coherent topics than existing ones while maintaining the diversity of the induced topics. Furthermore, we found that the inferred topics cover the input texts to some extent, while hallucinated topics are hardly generated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doi-etal-2024-topic">
<titleInfo>
<title>Topic Modeling for Short Texts with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomoki</namePart>
<namePart type="family">Doi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaru</namePart>
<namePart type="family">Isonuma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitomi</namePart>
<namePart type="family">Yanaka</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 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiyan</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eve</namePart>
<namePart type="family">Fleisig</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>As conventional topic models rely on word co-occurrence to infer latent topics, topic modeling for short texts has been a long-standing challenge. Large Language Models (LLMs) can potentially overcome this challenge by contextually learning the meanings of words via pretraining. In this paper, we study two approaches to using LLMs for topic modeling: parallel prompting and sequential prompting. Input length limitations prevent LLMs from processing many texts at once. However, an arbitrary number of texts can be handled by LLMs by splitting the texts into smaller subsets and processing them in parallel or sequentially. Our experimental results demonstrate that our methods can identify more coherent topics than existing ones while maintaining the diversity of the induced topics. Furthermore, we found that the inferred topics cover the input texts to some extent, while hallucinated topics are hardly generated.</abstract>
<identifier type="citekey">doi-etal-2024-topic</identifier>
<location>
<url>https://aclanthology.org/2024.acl-srw.3</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>21</start>
<end>33</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Topic Modeling for Short Texts with Large Language Models
%A Doi, Tomoki
%A Isonuma, Masaru
%A Yanaka, Hitomi
%Y Fu, Xiyan
%Y Fleisig, Eve
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F doi-etal-2024-topic
%X As conventional topic models rely on word co-occurrence to infer latent topics, topic modeling for short texts has been a long-standing challenge. Large Language Models (LLMs) can potentially overcome this challenge by contextually learning the meanings of words via pretraining. In this paper, we study two approaches to using LLMs for topic modeling: parallel prompting and sequential prompting. Input length limitations prevent LLMs from processing many texts at once. However, an arbitrary number of texts can be handled by LLMs by splitting the texts into smaller subsets and processing them in parallel or sequentially. Our experimental results demonstrate that our methods can identify more coherent topics than existing ones while maintaining the diversity of the induced topics. Furthermore, we found that the inferred topics cover the input texts to some extent, while hallucinated topics are hardly generated.
%U https://aclanthology.org/2024.acl-srw.3
%P 21-33
Markdown (Informal)
[Topic Modeling for Short Texts with Large Language Models](https://aclanthology.org/2024.acl-srw.3) (Doi et al., ACL 2024)
ACL
- Tomoki Doi, Masaru Isonuma, and Hitomi Yanaka. 2024. Topic Modeling for Short Texts with Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 21–33, Bangkok, Thailand. Association for Computational Linguistics.