@inproceedings{liu-etal-2025-llm-guided,
title = "{LLM}-Guided Semantic-Aware Clustering for Topic Modeling",
author = "Liu, Jianghan and
Shang, Ziyu and
Ke, Wenjun and
Wang, Peng and
Luo, Zhizhao and
Liu, Jiajun and
Li, Guozheng and
Li, Yining",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.902/",
doi = "10.18653/v1/2025.acl-long.902",
pages = "18420--18435",
ISBN = "979-8-89176-251-0",
abstract = "Topic modeling aims to discover the distribution of topics within a corpus. The advanced comprehension and generative capabilities of large language models (LLMs) have introduced new avenues for topic modeling, particularly by prompting LLMs to generate topics and refine them by merging similar ones. However, this approach necessitates that LLMs generate topics with consistent granularity, thus relying on the exceptional instruction-following capabilities of closed-source LLMs (such as GPT-4) or requiring additional training. Moreover, merging based only on topic words and neglecting the fine-grained semantics within documents might fail to fully uncover the underlying topic structure. In this work, we propose a semi-supervised topic modeling method, LiSA, that combines LLMs with clustering to improve topic generation and distribution. Specifically, we begin with prompting LLMs to generate a candidate topic word for each document, thereby constructing a topic-level semantic space. To further utilize the mutual complementarity between them, we first cluster documents and candidate topic words, and then establish a mapping from document to topic in the LLM-guided assignment stage. Subsequently, we introduce a collaborative enhancement strategy to align the two semantic spaces and establish a better topic distribution. Experimental results demonstrate that LiSA outperforms state-of-the-art methods that utilize GPT-4 on topic alignment, and exhibits competitive performance compared to Neural Topic Models on topic quality. The codes are available at https://github.com/ljh986/LiSA."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-llm-guided">
<titleInfo>
<title>LLM-Guided Semantic-Aware Clustering for Topic Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianghan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyu</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjun</namePart>
<namePart type="family">Ke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhizhao</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guozheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yining</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>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Topic modeling aims to discover the distribution of topics within a corpus. The advanced comprehension and generative capabilities of large language models (LLMs) have introduced new avenues for topic modeling, particularly by prompting LLMs to generate topics and refine them by merging similar ones. However, this approach necessitates that LLMs generate topics with consistent granularity, thus relying on the exceptional instruction-following capabilities of closed-source LLMs (such as GPT-4) or requiring additional training. Moreover, merging based only on topic words and neglecting the fine-grained semantics within documents might fail to fully uncover the underlying topic structure. In this work, we propose a semi-supervised topic modeling method, LiSA, that combines LLMs with clustering to improve topic generation and distribution. Specifically, we begin with prompting LLMs to generate a candidate topic word for each document, thereby constructing a topic-level semantic space. To further utilize the mutual complementarity between them, we first cluster documents and candidate topic words, and then establish a mapping from document to topic in the LLM-guided assignment stage. Subsequently, we introduce a collaborative enhancement strategy to align the two semantic spaces and establish a better topic distribution. Experimental results demonstrate that LiSA outperforms state-of-the-art methods that utilize GPT-4 on topic alignment, and exhibits competitive performance compared to Neural Topic Models on topic quality. The codes are available at https://github.com/ljh986/LiSA.</abstract>
<identifier type="citekey">liu-etal-2025-llm-guided</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.902</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.902/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>18420</start>
<end>18435</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM-Guided Semantic-Aware Clustering for Topic Modeling
%A Liu, Jianghan
%A Shang, Ziyu
%A Ke, Wenjun
%A Wang, Peng
%A Luo, Zhizhao
%A Liu, Jiajun
%A Li, Guozheng
%A Li, Yining
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F liu-etal-2025-llm-guided
%X Topic modeling aims to discover the distribution of topics within a corpus. The advanced comprehension and generative capabilities of large language models (LLMs) have introduced new avenues for topic modeling, particularly by prompting LLMs to generate topics and refine them by merging similar ones. However, this approach necessitates that LLMs generate topics with consistent granularity, thus relying on the exceptional instruction-following capabilities of closed-source LLMs (such as GPT-4) or requiring additional training. Moreover, merging based only on topic words and neglecting the fine-grained semantics within documents might fail to fully uncover the underlying topic structure. In this work, we propose a semi-supervised topic modeling method, LiSA, that combines LLMs with clustering to improve topic generation and distribution. Specifically, we begin with prompting LLMs to generate a candidate topic word for each document, thereby constructing a topic-level semantic space. To further utilize the mutual complementarity between them, we first cluster documents and candidate topic words, and then establish a mapping from document to topic in the LLM-guided assignment stage. Subsequently, we introduce a collaborative enhancement strategy to align the two semantic spaces and establish a better topic distribution. Experimental results demonstrate that LiSA outperforms state-of-the-art methods that utilize GPT-4 on topic alignment, and exhibits competitive performance compared to Neural Topic Models on topic quality. The codes are available at https://github.com/ljh986/LiSA.
%R 10.18653/v1/2025.acl-long.902
%U https://aclanthology.org/2025.acl-long.902/
%U https://doi.org/10.18653/v1/2025.acl-long.902
%P 18420-18435
Markdown (Informal)
[LLM-Guided Semantic-Aware Clustering for Topic Modeling](https://aclanthology.org/2025.acl-long.902/) (Liu et al., ACL 2025)
ACL
- Jianghan Liu, Ziyu Shang, Wenjun Ke, Peng Wang, Zhizhao Luo, Jiajun Liu, Guozheng Li, and Yining Li. 2025. LLM-Guided Semantic-Aware Clustering for Topic Modeling. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 18420–18435, Vienna, Austria. Association for Computational Linguistics.