Papers › TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning

TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning

12 Jun 2025arXiv:2506.10380archive 2025-07-28

Xiaohan Yu, Pu Jian, Chong Chen

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 hybrid 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. We release TableRAG at https://github.com/yxh-y/TableRAG/tree/main.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

yxh-y/tablerag officialmentioned in paperSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TableRAG: Million-Token Table Understanding with Language Models (arXiv:2410.04739; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Answer GenerationChunkingOpen-Domain Question AnsweringQuestion AnsweringRAGRetrievalRetrieval-augmented GenerationText Retrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionAttention DropoutBARTBERTBPEDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionRAGSoftmaxWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections