arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2606.01255cs.CL

Agentic Clustering: 通过多智能体精炼实现可控文本分类

Agentic Clustering: Controllable Text Taxonomies via Multi-Agent Refinement

Burning Glass Institute(Burning Glass研究院);Harvard University(哈佛大学)

Simon Löwe, Emily Silcock

AI总结:

提出一种基于多智能体(提议者、合成者、审计者、调查者、批评者)的自适应文本聚类方法,通过编排器LLM动态调整聚类流程,在七个公开基准上实现最先进性能,ARI最高提升32%。

摘要:

最近的文本聚类方法使用大型语言模型从语料库中提出聚类分类法,然后将每个文本分配到其中。这些流程本质上是程序化的:LLM调用的顺序以及停止、合并和拆分聚类的规则是预先在代码中固定的,因此它们在不同结构的语料库上泛化能力差,并且难以整合用户提供的约束,如目标聚类数量或聚类意图。我们提出了一种基于智能体的替代方案,其中编排器LLM在每个步骤检查发现过程的状态,并调度一组专门的智能体(提议者、合成者、审计者、调查者和批评者)中的一个,使流程适应语料库,而不是执行固定的流程。在七个公开文本聚类基准上,该方法实现了最先进的性能,在ARI上比最强的先前LLM基线高出32%。

英文摘要:

Recent text-clustering methods use large language models to propose a cluster taxonomy from a corpus and then assign each text to it. These pipelines are fundamentally programmatic: the sequence of LLM calls and the rules for stopping, merging, and splitting clusters are fixed in code in advance, so they generalise poorly across corpora of different structure and cannot easily incorporate user-supplied constraints such as a target cluster count or a clustering intent. We propose an agentic alternative in which an orchestrator LLM inspects the state of the discovery process at each step and dispatches one of a small set of specialised agents - proposer, synthesizer, auditor, investigator, and critic - adapting the pipeline to the corpus rather than executing a fixed one. On seven public text-clustering benchmarks the method achieves state-of-the-art performance, beating the strongest prior LLM baseline by up to 32% in ARI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑