用大模型做聚类核心，结合嵌入引导，提升领域适应性。
ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation
- 以大模型为核心，嵌入方法仅作引导，降低调优成本。
- 在3个公开数据集和2个新领域数据集上均达领先效果。
- 适合需要领域知识注入的文本聚类场景，如医疗、法律。
文本聚类是自然语言处理的基础任务，但传统基于预训练嵌入的聚类算法在特定领域中常因缺乏成本高昂的微调而表现不佳。大语言模型（LLMs）具备强大的上下文推理能力，但以往工作多将其作为辅助模块，用于优化嵌入或调整聚类边界。本文提出ClusterFusion，一种将LLM作为聚类核心的混合框架，由轻量级嵌入方法进行引导。该框架分为三个阶段：嵌入引导的子集划分、LLM驱动的主题总结、以及基于LLM的主题分配。这一设计使领域知识与用户偏好可直接融入，充分释放了LLM的上下文适应能力。在三个公开基准和两个新构建的领域专用数据集上的实验表明，ClusterFusion不仅在标准任务上达到最先进水平，还在专业领域中取得显著提升。为支持后续研究，我们发布了新构建的数据集及所有基准结果。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。