用大模型生成可读的聚类描述，让非专家也能理解数据分组。
LangLasso: Interactive Cluster Descriptions through LLM Explanation
- 通过大语言模型生成自然语言描述聚类结构
- 相比传统方法更易理解，支持外部知识融合
- 适合无技术背景的研究者快速探索数据
降维是揭示数据结构与潜在聚类的强大工具。然而，由于坐标轴是特征的复杂非线性组合，往往缺乏语义可解释性。现有可视化分析（VA）方法通过特征对比和交互探索支持聚类解释，但需技术背景且耗时费力。我们提出LangLasso，一种结合大语言模型（LLMs）的交互式自然语言聚类描述新方法。该方法生成人类可读的描述，使非专家也能理解聚类，并可融入数据集之外的上下文知识。我们系统评估了解释的可靠性，结果表明LangLasso为更广泛用户参与聚类解释提供了有效起点。工具已开源：https://langlasso.vercel.app
原文摘要 · Abstract (English)
Dimensionality reduction is a powerful technique for revealing structure and potential clusters in data. However, as the axes are complex, non-linear combinations of features, they often lack semantic interpretability. Existing visual analytics (VA) methods support cluster interpretation through feature comparison and interactive exploration, but they require technical expertise and intense human effort. We present \textit{LangLasso}, a novel method that complements VA approaches through interactive, natural language descriptions of clusters using large language models (LLMs). It produces human-readable descriptions that make cluster interpretation accessible to non-experts and allow integration of external contextual knowledge beyond the dataset. We systematically evaluate the reliability of these explanations and demonstrate that \langlasso provides an effective first step for engaging broader audiences in cluster interpretation. The tool is available at https://langlasso.vercel.app
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。