mlsanityData to 14 Oct 2026

TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning

arXiv 2506.10380 ↗First posted 12 Jun 2025cs.CL cs.IRcited by 24

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

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

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 25 of its 40 references that are in the map. First posted on arXiv 12 Jun 2025.

Builds on

25 of 40 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables29 Jun
  2. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition15 Apr
  3. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding9 Jan
  4. 2023TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning14 Dec
  5. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning31 Jan

Other references · 20

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  6. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  7. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  8. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  9. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
  10. 2022Binding Language Models in Symbolic Languagescited by 228
  11. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 147
  12. 2024InfiAgent-DABench: Evaluating Agents on Data Analysis Taskscited by 140
8 more
  1. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  2. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 72
  3. 2024Large Language Model for Table Processing: A Surveycited by 52
  4. 2023Tab-CoT: Zero-shot Tabular Chain of Thoughtcited by 42
  5. 2024The Chronicles of RAG: The Retriever, the Chunk and the Generatorcited by 34
  6. 2024REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Modelscited by 23
  7. 2024Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchangecited by 22
  8. 2024PyTond: Efficient Python Data Science on the Shoulders of Databasescited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 15.

24 papers.

Sort:

By area:

  1. 2025LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Sciencecited by 15
  2. 2025Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoningcited by 10
  3. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 5
  4. 2025Dingtalk DeepResearch: A Unified Multi Agent Framework for Adaptive Intelligence in Enterprise Environmentscited by 5
  5. 2025PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agencycited by 3
  6. 2026A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challengescited by 3
  7. 2025An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEscited by 2
  8. 2025RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QAcited by 1
  9. 2025TabRAG: Improving Tabular Document Question Answering for Retrieval Augmented Generation via Structured Representationscited by 1
  10. 2026TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignmentcited by 1
  11. 2026Overcoming the "Impracticality" of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic Frameworkcited by 1
  12. 2026Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answeringcited by 1
12 more
  1. 2026HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Documentcited by 1
  2. 2025SQuARE: Structured Query & Adaptive Retrieval Engine For Tabular Formatscited by 0
  3. 2026Agentic DAG-Orchestrated Planner Framework for Multi-Modal, Multi-Hop Question Answering in Hybrid Data Lakescited by 0
  4. 2026FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoningcited by 0
  5. 2026Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systemscited by 0
  6. 2026A Picture is Worth a Thousand Words? An Empirical Study of Aggregation Strategies for Visual Financial Document Retrievalcited by 0
  7. 2026ChartWalker: Benchmarking the Cross-Chart RAG Task with Hierarchical Knowledge Graphscited by 0
  8. 2026Semantically Similar, Logically Distinct: Diagnosing the Semantic-Answerability Gap in Table RAGcited by 0
  9. 2026Hierarchical Reranking for Scalable Financial RAG Systemcited by 0
  10. 2026Think Inside the Chunk: RegulaRAG for Regulation-Compliant Scenario Generation using LLMs: A Case Study of UN Regulation No. 152cited by 0
  11. 2026VIGIL: Verifier-Informed Gated Improvement Loop for Spreadsheet Question Answeringcited by 0
  12. 2026ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contractscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DBRAG: Multi-Table Retrieval-Augmented Generation for Complex Database Queries
  2. 2025mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
  3. 2025BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents
  4. 2025T2-RAGBench: Text-and-Table Benchmark for Evaluating Retrieval-Augmented Generation
  5. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
  6. 2026When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problems
  7. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
  8. 2025HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation