用大模型提升表格数据聚类的语义理解，兼顾速度与准确性
GRACE: LLM-Grounded Semantic Metric Spaces for Scalable Mixed-Data Clustering
- 通过多视角大模型查询，将异构数据映射到统一语义空间
- 单次调用完成语义注入，计算开销仅为传统方法1/10
- 适合需要可解释性聚类的金融、医疗等跨领域应用
混合类型表格数据聚类需统一度量空间以弥合连续数值与离散符号间的固有差异。传统方法完全依赖数据内部统计估计类别关系，局限于经验共现模式，忽略概念上明显但统计未观测到的关联。尽管大语言模型（LLM）提供外部世界知识，但将其文本推理应用于高度抽象的表格概念仍具挑战。通常需将LLM嵌入迭代度量学习循环以动态优化跨模态表示，导致难以承受的计算开销，迫使在语义丰富性与可扩展性之间妥协。为此，我们提出GRACE——一种基于大模型的可扩展混合数据聚类框架。GRACE通过多视角大模型查询策略，将属性值层面的异构信息转化为知识驱动的描述，实现一次性的语义锚定，生成通用语义表征并嵌入统一空间，从而将昂贵的LLM调用与迭代优化解耦。此外，GRACE通过交叉验证外部语义与数据内部统计证据，确保其与数据集特定聚类结构一致。最终，GRACE在保持传统统计基线可扩展性的基础上，在11种对比方法中实现了更优的聚类准确率与概念可解释性。源码见：https://github.com/develop-yang/GRACE-GRACE-A
原文摘要 · Abstract (English)
Clustering mixed tabular data requires a unified metric space to bridge the inherent heterogeneity between continuous numerical measurements and discrete categorical symbols. Traditionally, algorithms rely entirely on dataset-internal statistics to estimate categorical relationships, which confines the learned metric to empirical co-occurrences and ignores conceptually obvious yet statistically unobserved affinities. Although LLMs offer external world knowledge, applying their text-centric reasoning to highly abstract tabular concepts presents significant challenges. Bridging this modality gap to construct a semantically complete metric typically requires embedding LLMs into iterative metric learning loops to dynamically optimize cross-modality representations. This incurs intractable computational overhead, forcing a compromise between semantic enrichment and scalability. Therefore, we propose GRACE, an LLM-grounded framework for scalable mixed-data clustering. GRACE shifts semantic acquisition to the attribute-value level via a multi-perspective LLM querying strategy, mapping heterogeneous values into knowledge-informed descriptions. Crucially, this one-shot grounding extracts general-purpose semantic representations that embed heterogeneous attributes into a unified space, decoupling expensive LLM invocation from iterative optimization. Furthermore, GRACE cross-validates these external semantics against dataset-internal statistical evidence to ensure alignment with the dataset-specific cluster structure. Ultimately, GRACE matches the scalability of conventional statistics-driven baselines while achieving superior clustering accuracy and conceptual interpretability over 11 competing methods. The source code is available at https://github.com/develop-yang/GRACE-GRACE-A
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。