TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning

ACL ARR 2025 May Submission1395 Authors

Abstract: Retrieval-Augmented Generation (RAG) has demonstrated considerable effectiveness in open-domain question answering. However, when applied to heterogeneous documents, comprising both textual and tabular components, existing RAG approaches exhibit critical limitations. The prevailing practice of flattening tables and chunking strategies disrupts the intrinsic tabular structure, leads to information loss, and undermines the reasoning capabilities of LLMs in multi-hop, global queries. To address these challenges, we propose TableRAG, an SQL-based framework that unifies textual understanding and complex manipulations over tabular data. TableRAG iteratively operates in four steps: context-sensitive query decomposition, text retrieval, SQL programming and execution, and compositional intermediate answer generation. We also develop HeteQA, a novel benchmark designed to evaluate the multi-hop heterogeneous reasoning capabilities. Experimental results demonstrate that TableRAG consistently outperforms existing baselines on both public datasets and our HeteQA, establishing a new state-of-the-art for heterogeneous document question answering.

Paper Type: Long

Research Area: Question Answering

Research Area Keywords: Language Modeling,Question Answering

Contribution Types: NLP engineering experiment, Reproduction study, Data resources, Data analysis

Languages Studied: English

Submission Number: 1395