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.

翻译：本文提出了k-NLPmeans与k-LLMmeans两种文本聚类方法，它们作为k-means的变体，通过周期性将数值质心替换为文本摘要来实现聚类。其核心思想——"摘要即质心"——在保持嵌入空间中k-means分配机制的同时，生成人类可读、可审计的聚类原型。该方法对大型语言模型（LLM）的使用具有可选性：k-NLPmeans采用轻量级确定性摘要生成器，支持离线、低成本和稳定的运行；k-LLMmeans则作为即插即用的升级方案，在固定单次迭代预算下使用LLM生成摘要，其成本不随数据集规模增长。我们还提出了适用于流式文本实时聚类的迷你批次扩展方法。在多种数据集、嵌入模型和摘要生成策略的测试中，本方法始终优于经典基线，并在无需大量调用LLM的情况下达到了近期基于LLM的聚类方法的准确度。最后，我们提供了针对序列化文本流的案例研究，并发布了基于StackExchange数据构建的流式文本聚类评估基准。