@inproceedings{zhang-etal-2025-llmtaxo,
title = "{LLMT}axo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media",
author = "Zhang, Haiqi and
Zhu, Zhengyuan and
Zhang, Zeyu and
Li, Chengkai",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1007/",
doi = "10.18653/v1/2025.findings-acl.1007",
pages = "19627--19641",
ISBN = "979-8-89176-256-5",
abstract = "With the rapid expansion of content on social media platforms, analyzing and comprehending online discourse has become increasingly complex. This paper introduces LLMTaxo, a novel framework leveraging large language models for the automated construction of taxonomies of factual claims from social media by generating topics at multiple levels of granularity. The resulting hierarchical structure significantly reduces redundancy and improves information accessibility. We also propose dedicated taxonomy evaluation metrics to enable comprehensive assessment. Evaluations conducted on three diverse datasets demonstrate LLMTaxo{'}s effectiveness in producing clear, coherent, and comprehensive taxonomies. Among the evaluated models, GPT-4o mini consistently outperforms others across most metrics. The framework{'}s flexibility and low reliance on manual intervention underscore its potential for broad applicability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-llmtaxo">
<titleInfo>
<title>LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haiqi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyuan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengkai</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>With the rapid expansion of content on social media platforms, analyzing and comprehending online discourse has become increasingly complex. This paper introduces LLMTaxo, a novel framework leveraging large language models for the automated construction of taxonomies of factual claims from social media by generating topics at multiple levels of granularity. The resulting hierarchical structure significantly reduces redundancy and improves information accessibility. We also propose dedicated taxonomy evaluation metrics to enable comprehensive assessment. Evaluations conducted on three diverse datasets demonstrate LLMTaxo’s effectiveness in producing clear, coherent, and comprehensive taxonomies. Among the evaluated models, GPT-4o mini consistently outperforms others across most metrics. The framework’s flexibility and low reliance on manual intervention underscore its potential for broad applicability.</abstract>
<identifier type="citekey">zhang-etal-2025-llmtaxo</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1007</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1007/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>19627</start>
<end>19641</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media
%A Zhang, Haiqi
%A Zhu, Zhengyuan
%A Zhang, Zeyu
%A Li, Chengkai
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F zhang-etal-2025-llmtaxo
%X With the rapid expansion of content on social media platforms, analyzing and comprehending online discourse has become increasingly complex. This paper introduces LLMTaxo, a novel framework leveraging large language models for the automated construction of taxonomies of factual claims from social media by generating topics at multiple levels of granularity. The resulting hierarchical structure significantly reduces redundancy and improves information accessibility. We also propose dedicated taxonomy evaluation metrics to enable comprehensive assessment. Evaluations conducted on three diverse datasets demonstrate LLMTaxo’s effectiveness in producing clear, coherent, and comprehensive taxonomies. Among the evaluated models, GPT-4o mini consistently outperforms others across most metrics. The framework’s flexibility and low reliance on manual intervention underscore its potential for broad applicability.
%R 10.18653/v1/2025.findings-acl.1007
%U https://aclanthology.org/2025.findings-acl.1007/
%U https://doi.org/10.18653/v1/2025.findings-acl.1007
%P 19627-19641
Markdown (Informal)
[LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media](https://aclanthology.org/2025.findings-acl.1007/) (Zhang et al., Findings 2025)
ACL