@inproceedings{jo-etal-2025-zerodl,
title = "{Z}ero{DL}: Zero-shot Distribution Learning for Text Clustering via Large Language Models",
author = "Jo, Hwiyeol and
Lee, Hyunwoo and
Yoo, Kang Min and
Park, Taiwoo",
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.1005/",
doi = "10.18653/v1/2025.findings-acl.1005",
pages = "19597--19607",
ISBN = "979-8-89176-256-5",
abstract = "The advancements in large language models (LLMs) have brought significant progress in NLP tasks. However, if a task cannot be fully described in prompts, the models could fail to carry out the task. In this paper, we propose a simple yet effective method to contextualize a task toward a LLM. The method utilizes (1) open-ended zero-shot inference from the entire dataset, (2) aggregate the inference results, and (3) finally incorporate the aggregated meta-information for the actual task. We show the effectiveness in text clustering tasks, empowering LLMs to perform text-to-text-based clustering and leading to improvements on several datasets. Furthermore, we explore the generated class labels for clustering, showing how the LLM understands the task through data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jo-etal-2025-zerodl">
<titleInfo>
<title>ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hwiyeol</namePart>
<namePart type="family">Jo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunwoo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="given">Min</namePart>
<namePart type="family">Yoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taiwoo</namePart>
<namePart type="family">Park</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>The advancements in large language models (LLMs) have brought significant progress in NLP tasks. However, if a task cannot be fully described in prompts, the models could fail to carry out the task. In this paper, we propose a simple yet effective method to contextualize a task toward a LLM. The method utilizes (1) open-ended zero-shot inference from the entire dataset, (2) aggregate the inference results, and (3) finally incorporate the aggregated meta-information for the actual task. We show the effectiveness in text clustering tasks, empowering LLMs to perform text-to-text-based clustering and leading to improvements on several datasets. Furthermore, we explore the generated class labels for clustering, showing how the LLM understands the task through data.</abstract>
<identifier type="citekey">jo-etal-2025-zerodl</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1005</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1005/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>19597</start>
<end>19607</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models
%A Jo, Hwiyeol
%A Lee, Hyunwoo
%A Yoo, Kang Min
%A Park, Taiwoo
%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 jo-etal-2025-zerodl
%X The advancements in large language models (LLMs) have brought significant progress in NLP tasks. However, if a task cannot be fully described in prompts, the models could fail to carry out the task. In this paper, we propose a simple yet effective method to contextualize a task toward a LLM. The method utilizes (1) open-ended zero-shot inference from the entire dataset, (2) aggregate the inference results, and (3) finally incorporate the aggregated meta-information for the actual task. We show the effectiveness in text clustering tasks, empowering LLMs to perform text-to-text-based clustering and leading to improvements on several datasets. Furthermore, we explore the generated class labels for clustering, showing how the LLM understands the task through data.
%R 10.18653/v1/2025.findings-acl.1005
%U https://aclanthology.org/2025.findings-acl.1005/
%U https://doi.org/10.18653/v1/2025.findings-acl.1005
%P 19597-19607
Markdown (Informal)
[ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models](https://aclanthology.org/2025.findings-acl.1005/) (Jo et al., Findings 2025)
ACL