让大模型自带动态记忆，自动判断聚类数量并优化结果。
LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering
- 用动态记忆让大模型记住迭代过程，持续优化聚类。
- 无需调参，在多个数据集上超越现有方法表现。
- 适合想用大模型做端到端文本聚类的研究者和工程师。
大型语言模型（LLMs）凭借其深层语义理解能力，正在重塑无监督学习，能够基于语义进行文本聚类。然而，直接应用受限于缺乏状态记忆以支持迭代优化，以及难以控制聚类粒度。现有方法常依赖复杂外部模块构成的流水线，牺牲了真正的端到端特性。我们提出 LLM-MemCluster，将聚类重构为完全由大模型原生完成的任务。该框架引入动态记忆以增强状态感知，并采用双提示策略，使模型能自主推理并决定聚类数量。在多个基准数据集上的评估表明，该无调参框架显著且一致地优于强基线。LLM-MemCluster 提供了一种高效、可解释且真正端到端的大模型文本聚类新范式。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are reshaping unsupervised learning by offering an unprecedented ability to perform text clustering based on their deep semantic understanding. However, their direct application is fundamentally limited by a lack of stateful memory for iterative refinement and the difficulty of managing cluster granularity. As a result, existing methods often rely on complex pipelines with external modules, sacrificing a truly end-to-end approach. We introduce LLM-MemCluster, a novel framework that reconceptualizes clustering as a fully LLM-native task. It leverages a Dynamic Memory to instill state awareness and a Dual-Prompt Strategy to enable the model to reason about and determine the number of clusters. Evaluated on several benchmark datasets, our tuning-free framework significantly and consistently outperforms strong baselines. LLM-MemCluster presents an effective, interpretable, and truly end-to-end paradigm for LLM-based 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。