用文本摘要代替聚类中心，让结果既可读又高效。
Summaries as Centroids for Interpretable and Scalable Text Clustering
- 用摘要替代数值中心点，保持嵌入空间聚类效果
- 在多个数据集上优于传统方法，接近LLM强模型性能
- 支持离线与实时流式处理，适合需要可解释性的场景
我们提出k-NLPmeans和k-LLMmeans，是k-means的文本聚类变体，定期用文本摘要替换数值中心点。核心思想是‘摘要作为中心’，在保留嵌入空间聚类分配的同时生成人类可读、可审计的簇原型。该方法可选使用大语言模型：k-NLPmeans采用轻量级确定性摘要器，实现离线、低成本、稳定运行；k-LLMmeans为即插即用升级版，在每轮固定预算内使用LLM生成摘要，成本不随数据集规模增长。此外，我们还提出了小批量扩展，用于实时流式文本聚类。在多种数据集、嵌入模型和摘要策略下，本方法始终优于经典基线，且接近近期基于LLM的聚类性能，同时避免大量调用LLM。最后，我们在序列文本流上进行了案例研究，并发布了一个基于StackExchange的基准数据集，用于评估流式文本聚类。
原文摘要 · Abstract (English)
We introduce k-NLPmeans and k-LLMmeans, text-clustering variants of k-means that periodically replace numeric centroids with textual summaries. The key idea, summary-as-centroid, retains k-means assignments in embedding space while producing human-readable, auditable cluster prototypes. The method is LLM-optional: k-NLPmeans uses lightweight, deterministic summarizers, enabling offline, low-cost, and stable operation; k-LLMmeans is a drop-in upgrade that uses an LLM for summaries under a fixed per-iteration budget whose cost does not grow with dataset size. We also present a mini-batch extension for real-time clustering of streaming text. Across diverse datasets, embedding models, and summarization strategies, our approach consistently outperforms classical baselines and approaches the accuracy of recent LLM-based clustering-without extensive LLM calls. Finally, we provide a case study on sequential text streams and release a StackExchange-derived benchmark for evaluating streaming text clustering.
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。