# GRACE: LLM-Grounded Semantic Metric Spaces for Scalable Mixed-Data Clustering

arXiv: https://arxiv.org/abs/2608.07881 · HTML: https://mlsanity.com/paper/2608.07881/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 52 references that are in the map.
- First posted on arXiv 8 Aug 2026.

## Builds on (most cited first, 28 of 28)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering](https://mlsanity.com/paper/2305.03403/) (2023)
- [Supporting Clustering with Contrastive Learning](https://mlsanity.com/paper/2103.12953/) (2021)
- [Entity Embeddings of Categorical Variables](https://mlsanity.com/paper/1604.06737/) (2016)
- [Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning](https://mlsanity.com/paper/2404.09491/) (2024)
- [Large Language Models Enable Few-Shot Clustering](https://mlsanity.com/paper/2307.00524/) (2023)
- [ClusterLLM: Large Language Models as a Guide for Text Clustering](https://mlsanity.com/paper/2305.14871/) (2023)
- [TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation](https://mlsanity.com/paper/2410.20626/) (2024)
- [Image Clustering with External Guidance](https://mlsanity.com/paper/2310.11989/) (2023)
- [Interpretable Deep Clustering for Tabular Data](https://mlsanity.com/paper/2306.04785/) (2023)
- [Hierarchical Vector Quantization for Unsupervised Action Segmentation](https://mlsanity.com/paper/2412.17640/) (2024)
- [Generalized Category Discovery with Large Language Models in the Loop](https://mlsanity.com/paper/2312.10897/) (2023)
- [Unsupervised Heterogeneous Coupling Learning for Categorical Representation](https://mlsanity.com/paper/2007.10720/) (2020)
- [A Simple Approach to Automated Spectral Clustering](https://mlsanity.com/paper/2107.12183/) (2021)
- [Robust Categorical Data Clustering Guided by Multi-Granular Competitive Learning](https://mlsanity.com/paper/2601.16491/) (2026)
- [Text-Guided Image Clustering](https://mlsanity.com/paper/2402.02996/) (2024)
- [Categorical Data Clustering via Value Order Estimated Distance Metric Learning](https://mlsanity.com/paper/2411.15189/) (2024)
- [Break the Tie: Learning Cluster-Customized Category Relationships for Categorical Data Clustering](https://mlsanity.com/paper/2511.09049/) (2025)
- [Learning Unified Distance Metric for Heterogeneous Attribute Data Clustering](https://mlsanity.com/paper/2603.04458/) (2026)
- [Learning Order Forest for Qualitative-Attribute Data Clustering](https://mlsanity.com/paper/2603.03387/) (2026)
- [Information-Theoretic Generative Clustering of Documents](https://mlsanity.com/paper/2412.13534/) (2024)
- [Bridging the Semantic Gap for Categorical Data Clustering via Large Language Models](https://mlsanity.com/paper/2601.01162/) (2026)
- [SpeHeatal: A Cluster-Enhanced Segmentation Method for Sperm Morphology Analysis](https://mlsanity.com/paper/2502.13192/) (2025)
- [Mixed Data Clustering Survey and Challenges](https://mlsanity.com/paper/2512.03070/) (2025)

## Abstract (arXiv)

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