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

翻译：降维是一种揭示数据结构和潜在聚类的强大技术。然而，由于坐标轴是特征之间复杂、非线性的组合，它们通常缺乏语义可解释性。现有的可视分析（VA）方法通过特征比较和交互式探索来支持聚类解释，但这些方法需要专业知识且耗费大量人力。我们提出 \textit{LangLasso}，这是一种新颖的方法，它利用大语言模型（LLMs）生成交互式的、自然语言的聚类描述，从而对VA方法进行补充。该方法生成易于人类理解的描述，使得非专家也能进行聚类解释，并允许整合数据集之外的外部上下文知识。我们系统评估了这些解释的可靠性，并证明 \langlasso 为吸引更广泛的受众参与聚类解释提供了一个有效的初步工具。该工具可在 https://langlasso.vercel.app 获取。