Beyond pure text, a substantial amount of knowledge is stored in tables. In real-world scenarios, user questions often require retrieving answers that are distributed across multiple tables. GraphRAG has recently attracted much attention for enhancing LLMs' reasoning capabilities by organizing external knowledge to address ad-hoc and complex questions, exemplifying a promising direction for cross-table question answering. In this paper, to address the current gap in available data, we first introduce a multi-table benchmark, MutliTableQA, comprising 60k tables and 25k user queries collected from real-world sources. Then, we propose the first Graph-Table-RAG framework, namely GTR, which reorganizes table corpora into a heterogeneous graph, employs a hierarchical coarse-to-fine retrieval process to extract the most relevant tables, and integrates graph-aware prompting for downstream LLMs' tabular reasoning. Extensive experiments show that GTR exhibits superior cross-table question-answering performance while maintaining high deployment efficiency, demonstrating its real-world practical applicability.
View on arXiv@article{zou2025_2504.01346,
title={ GTR: Graph-Table-RAG for Cross-Table Question Answering },
author={ Jiaru Zou and Dongqi Fu and Sirui Chen and Xinrui He and Zihao Li and Yada Zhu and Jiawei Han and Jingrui He },
journal={arXiv preprint arXiv:2504.01346},
year={ 2025 }
}