LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Yuanjie, Yang, Liangwei, Xu, Ke, Zhang, Weizhi, Song, Zihe, Wang, Jindong, Yu, Philip S.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917388157452288
author Zhu, Yuanjie
Yang, Liangwei
Xu, Ke
Zhang, Weizhi
Song, Zihe
Wang, Jindong
Yu, Philip S.
author_facet Zhu, Yuanjie
Yang, Liangwei
Xu, Ke
Zhang, Weizhi
Song, Zihe
Wang, Jindong
Yu, Philip S.
contents Large Language Models (LLMs) are reshaping unsupervised learning by offering an unprecedented ability to perform text clustering based on their deep semantic understanding. However, their direct application is fundamentally limited by a lack of stateful memory for iterative refinement and the difficulty of managing cluster granularity. As a result, existing methods often rely on complex pipelines with external modules, sacrificing a truly end-to-end approach. We introduce LLM-MemCluster, a novel framework that reconceptualizes clustering as a fully LLM-native task. It leverages a Dynamic Memory to instill state awareness and a Dual-Prompt Strategy to enable the model to reason about and determine the number of clusters. Evaluated on several benchmark datasets, our tuning-free framework significantly and consistently outperforms strong baselines. LLM-MemCluster presents an effective, interpretable, and truly end-to-end paradigm for LLM-based text clustering.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15424
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering
Zhu, Yuanjie
Yang, Liangwei
Xu, Ke
Zhang, Weizhi
Song, Zihe
Wang, Jindong
Yu, Philip S.
Computation and Language
Large Language Models (LLMs) are reshaping unsupervised learning by offering an unprecedented ability to perform text clustering based on their deep semantic understanding. However, their direct application is fundamentally limited by a lack of stateful memory for iterative refinement and the difficulty of managing cluster granularity. As a result, existing methods often rely on complex pipelines with external modules, sacrificing a truly end-to-end approach. We introduce LLM-MemCluster, a novel framework that reconceptualizes clustering as a fully LLM-native task. It leverages a Dynamic Memory to instill state awareness and a Dual-Prompt Strategy to enable the model to reason about and determine the number of clusters. Evaluated on several benchmark datasets, our tuning-free framework significantly and consistently outperforms strong baselines. LLM-MemCluster presents an effective, interpretable, and truly end-to-end paradigm for LLM-based text clustering.
title LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering
topic Computation and Language
url https://arxiv.org/abs/2511.15424