返回全部动态

LUCID:基于LLM的可解释无监督社区检测方法

原标题:Interpretable Unsupervised Community Detection with LLM-Symbolized Structured Processes

arXiv cs.AI一手来源研究质量 83

AI 摘要

arXiv 上发布了一项名为 LUCID 的研究,提出了一种基于大语言模型(LLM)的可解释无监督社区检测方法。该方法受相变动力学启发,设计为四阶段流程,利用 LLM 生成显式规则,无需训练数据和标签。实验表明,LUCID 在真实数据集上达到了最先进性能,优于领先的无监督和半监督基线。

以上摘要由 AI 生成,可能存在误差。事实请以原文为准。

正文节选

Computer Science > Artificial Intelligence Title:Interpretable Unsupervised Community Detection with LLM-Symbolized Structured Processes View PDF HTML (experimental) Abstract:Community detection is a fundamental task in graph analytics that aims to identify cohesive groups of entities with similar behaviors or interests. Classic objective-driven methods struggle with complex graph structures, while deep-learning approaches improve performance at the expense of interpretability and re


发布时间:2026-08-10 12:00
抓取时间:2026-08-10 12:01
来源机构:arXiv
阅读原文arxiv.org