mlsanityData to 7 Oct 2026

TableRAG: Million-Token Table Understanding with Language Models

arXiv 2410.04739 ↗First posted 7 Oct 2024cs.CL cs.AI cs.IRcited by 40

Not on the map. Why?

Abstract (arXiv)

Recent advancements in language models (LMs) have notably enhanced their ability to reason with tabular data, primarily through program-aided mechanisms that manipulate and analyze tables. However, these methods often require the entire table as input, leading to scalability challenges due to the positional bias or context length constraints. In response to these challenges, we introduce TableRAG, a Retrieval-Augmented Generation (RAG) framework specifically designed for LM-based table understanding. TableRAG leverages query expansion combined with schema and cell retrieval to pinpoint crucial information before providing it to the LMs. This enables more efficient data encoding and precise retrieval, significantly reducing prompt lengths and mitigating information loss. We have developed two new million-token benchmarks from the Arcade and BIRD-SQL datasets to thoroughly evaluate TableRAG's effectiveness at scale. Our results demonstrate that TableRAG's retrieval design achieves the highest retrieval quality, leading to the new state-of-the-art performance on large-scale table understanding.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 24 of its 31 references that are in the map. First posted on arXiv 7 Oct 2024.

Builds on

24 of 31 references.

References · 24

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  5. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  6. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  7. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  8. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  9. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  10. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 425
  11. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  12. 2022Binding Language Models in Symbolic Languagescited by 224
12 more
  1. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 185
  2. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 177
  3. 2023Query2doc: Query Expansion with Large Language Modelscited by 146
  4. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 136
  5. 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
  6. 2022Natural Language to Code Generation in Interactive Data Science Notebookscited by 86
  7. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  8. 2020Understanding tables with intermediate pre-trainingcited by 68
  9. 2024DTS-SQL: Decomposed Text-to-SQL with Small Large Language Modelscited by 45
  10. 2023Rethinking Tabular Data Understanding with Large Language Modelscited by 34
  11. 2023MultiTabQA: Generating Tabular Answers for Multi-Table Question Answeringcited by 32
  12. 2023TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoningcited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 26; 2026: 10.

40 papers.

Sort:

By area:

  1. 2025Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Modelscited by 46
  2. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  3. 2025From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agentscited by 27
  4. 2024LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputationcited by 25
  5. 2024Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understandingcited by 20
  6. 2024TQA-Bench: Evaluating LLMs for Multi-Table Question Answeringcited by 17
  7. 2025TARGET: Benchmarking Table Retrieval for Generative Taskscited by 17
  8. 2025Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQLcited by 14
  9. 2025AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understandingcited by 14
  10. 2025When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tablescited by 10
  11. 2025NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tablescited by 8
  12. 2026Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Searchcited by 8
28 more
  1. 2025Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaborationcited by 4
  2. 2025AutoPK: Leveraging LLMs and a Hybrid Similarity Metric for Advanced Retrieval of Pharmacokinetic Data from Complex Tables and Documentscited by 4
  3. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 4
  4. 2025How Good Are LLMs at Processing Tool Outputs?cited by 4
  5. 2025Improving Table Understanding with LLMs and Entity-Oriented Searchcited by 3
  6. 2025TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answeringcited by 3
  7. 2025Same Content, Different Representations: A Controlled Study for Table QAcited by 3
  8. 2025Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimizationcited by 3
  9. 2025Towards Question Answering over Large Semi-structured Tablescited by 2
  10. 2025MRT at SemEval-2025 Task 8: Maximizing Recovery from Tables with Multiple Stepscited by 2
  11. 2025Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligencecited by 2
  12. 2026Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language Modelscited by 2
  13. 2025Towards Probabilistic Question Answering Over Tabular Datacited by 1
  14. 2025What to Keep and What to Drop: Adaptive Table Filtering Frameworkcited by 1
  15. 2024An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problemscited by 0
  16. 2025Evaluating VisualRAG: Quantifying Cross-Modal Performance in Enterprise Document Understandingcited by 0
  17. 2025MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Stepscited by 0
  18. 2025Scan-do Attitude: Towards Autonomous CT Protocol Management using a Large Language Model Agentcited by 0
  19. 2025NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimization Framework with LLMs for NOTAM Interpretationcited by 0
  20. 2025JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Modelscited by 0
  21. 2026Improving Large Molecular Language Model via Relation-aware Multimodal Collaborationcited by 0
  22. 2026A Multi-Agent Approach for Claim Verification from Tabular Data Documentscited by 0
  23. 2026Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tablescited by 0
  24. 2026Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learningcited by 0
  25. 2026SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extractioncited by 0
  26. 2026Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answeringcited by 0
  27. 2026EdgeLM: Edge Demonstrations for Language Models' Table Understandingcited by 0
  28. 2026TabScope: Question-Adaptive Scope Selection for Table Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Efficient Table Retrieval and Understanding with Multimodal Large Language Models
  2. 2026DBRAG: Multi-Table Retrieval-Augmented Generation for Complex Database Queries
  3. 2025Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System
  4. 2025RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking
  5. 2025Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges
  6. 2026FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning
  7. 2025TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning
  8. 2025Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB