arXiv cs.CL· Yiming Xu, Yuan Yuan, Vijay Viswanathan, Graham Neubig·· 13 小时前AI 评分31
ClusterFusion：嵌入引导与 LLM 适配的混合聚类框架
ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation
AI 导读
ClusterFusion 提出一种以 LLM 为聚类核心、轻量嵌入方法为引导的混合聚类框架，分嵌入引导子集划分、LLM 驱动主题摘要、LLM 主题分配三阶段。在三个公开基准和两个新构建的领域数据集上，该方法在标准任务上达到 SOTA，并在专业领域取得显著提升。团队已公开新数据集及全部基准结果。
正文 · 原文
Abstract: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.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2512.04350 [cs.CL] |
| (or arXiv:2512.04350v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2512.04350 arXiv-issued DOI via DataCite |
Submission history
From: Yiming Xu [view email]
[v1]
Thu, 4 Dec 2025 00:49:43 UTC (1,490 KB)
[v2]
Tue, 20 Oct 2026 21:20:15 UTC (1,399 KB)
来源：arXiv cs.CL · arxiv.org