CGPT: Cluster-Guided Partial Tables with LLM-Generated Supervision for Table Retrieval

TL;DR

CGPT introduces a novel training framework that leverages LLM-generated synthetic queries and clustering-based partial tables to significantly improve large-scale table retrieval performance across multiple benchmarks.

Contribution

The paper proposes a new method that uses clustering and LLM-generated supervision to enhance table retrieval, outperforming existing baselines and demonstrating strong cross-domain generalization.

Findings

Achieves an average R@1 improvement of 16.54% over baselines.

Outperforms previous methods like QGpT on four public benchmarks.

Remains effective with smaller LLMs for synthetic query generation.

Abstract

General-purpose embedding models have demonstrated strong performance in text retrieval but remain suboptimal for table retrieval, where highly structured content leads to semantic compression and query-table mismatch. Recent LLM-based retrieval augmentation methods mitigate this issue by generating synthetic queries, yet they often rely on heuristic partial-table selection and seldom leverage these synthetic queries as supervision to improve the embedding model. We introduce CGPT, a training framework that enhances table retrieval through LLM-generated supervision. CGPT constructs semantically diverse partial tables by clustering table instances using K-means and sampling across clusters to broaden semantic coverage. An LLM then generates synthetic queries for these partial tables, which are used in hard-negative contrastive fine-tuning to refine the embedding model. Experiments across four public benchmarks (MimoTable, OTTQA, FetaQA, and E2E-WTQ) show that CGPT consistently outperforms retrieval baselines, including QGpT, with an average R@1 improvement of 16.54 percent. In a unified multi-domain corpus setting, CGPT further demonstrates strong cross-domain generalization and remains effective even when using smaller LLMs for synthetic query generation. These results indicate that semantically guided partial-table construction, combined with contrastive training from LLM-generated supervision, provides an effective and scalable paradigm for large-scale table retrieval. Our code is available at https://github.com/yumeow0122/CGPT.