ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Yiming, Yuan, Yuan, Viswanathan, Vijay, Neubig, Graham
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917124291690496
author Xu, Yiming
Yuan, Yuan
Viswanathan, Vijay
Neubig, Graham
author_facet Xu, Yiming
Yuan, Yuan
Viswanathan, Vijay
Neubig, Graham
contents Text clustering is a fundamental task in natural language processing, yet traditional clustering algorithms with pre-trained embeddings often struggle in domain-specific contexts without costly fine-tuning. Large language models (LLMs) provide strong contextual reasoning, yet prior work mainly uses them as auxiliary modules to refine embeddings or adjust cluster boundaries. We propose ClusterFusion, a hybrid framework that instead treats the LLM as the clustering core, guided by lightweight embedding methods. The framework proceeds in three stages: embedding-guided subset partition, LLM-driven topic summarization, and LLM-based topic assignment. This design enables direct incorporation of domain knowledge and user preferences, fully leveraging the contextual adaptability of LLMs. Experiments on three public benchmarks and two new domain-specific datasets demonstrate that ClusterFusion not only achieves state-of-the-art performance on standard tasks but also delivers substantial gains in specialized domains. To support future work, we release our newly constructed dataset and results on all benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04350
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation
Xu, Yiming
Yuan, Yuan
Viswanathan, Vijay
Neubig, Graham
Computation and Language
Text clustering is a fundamental task in natural language processing, yet traditional clustering algorithms with pre-trained embeddings often struggle in domain-specific contexts without costly fine-tuning. Large language models (LLMs) provide strong contextual reasoning, yet prior work mainly uses them as auxiliary modules to refine embeddings or adjust cluster boundaries. We propose ClusterFusion, a hybrid framework that instead treats the LLM as the clustering core, guided by lightweight embedding methods. The framework proceeds in three stages: embedding-guided subset partition, LLM-driven topic summarization, and LLM-based topic assignment. This design enables direct incorporation of domain knowledge and user preferences, fully leveraging the contextual adaptability of LLMs. Experiments on three public benchmarks and two new domain-specific datasets demonstrate that ClusterFusion not only achieves state-of-the-art performance on standard tasks but also delivers substantial gains in specialized domains. To support future work, we release our newly constructed dataset and results on all benchmarks.
title ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation
topic Computation and Language
url https://arxiv.org/abs/2512.04350