mlsanityData to 14 Oct 2026

Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges

arXiv 2508.00217 ↗First posted 31 Jul 2025cs.CL cs.DB cs.LGcited by 10

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

Tables have gained significant attention in large language models (LLMs) and multimodal large language models (MLLMs) due to their complex and flexible structure. Unlike linear text inputs, tables are two-dimensional, encompassing formats that range from well-structured database tables to complex, multi-layered spreadsheets, each with different purposes. This diversity in format and purpose has led to the development of specialized methods and tasks, instead of universal approaches, making navigation of table understanding tasks challenging. To address these challenges, this paper introduces key concepts through a taxonomy of tabular input representations and an introduction of table understanding tasks. We highlight several critical gaps in the field that indicate the need for further research: (1) the predominance of retrieval-focused tasks that require minimal reasoning beyond mathematical and logical operations; (2) significant challenges faced by models when processing complex table structures, large-scale tables, length context, or multi-table scenarios; and (3) the limited generalization of models across different tabular representations and formats.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 79 of its 105 references that are in the map. First posted on arXiv 31 Jul 2025.

Builds on

79 of 105 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integration4 Nov

Other references · 78

  1. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  2. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  3. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  4. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  5. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  6. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  7. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  8. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 428
  9. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  10. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  11. 2023Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Modelscited by 357
  12. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 350
38 more
  1. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 268
  2. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
  3. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 235
  4. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 232
  5. 2017Challenges in Data-to-Document Generationcited by 226
  6. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 188
  7. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 178
  8. 2021FeTaQA: Free-form Table Question Answeringcited by 175
  9. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 167
  10. 2020Open Question Answering over Tables and Textcited by 163
  11. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 145
  12. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 137
  13. 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
  14. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Datacited by 121
  15. 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generationcited by 118
  16. 2021TABBIE: Pretrained Representations of Tabular Datacited by 111
  17. 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
  18. 2021KaggleDBQA: Realistic Evaluation of Text-to-SQL Parserscited by 106
  19. 2024Why Tabular Foundation Models Should Be a Research Prioritycited by 106
  20. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  21. 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
  22. 2020Logical Natural Language Generation from Open-Domain Tablescited by 90
  23. 2019Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challengecited by 86
  24. 2020INFOTABS: Inference on Tables as Semi-structured Datacited by 86
  25. 2019Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generationcited by 75
  26. 2024OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMscited by 72
  27. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  28. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
  29. 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustnesscited by 53
  30. 2024Large Language Model for Table Processing: A Surveycited by 52
  31. 2023SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tablescited by 51
  32. 2020AxCell: Automatic Extraction of Results from Machine Learning Paperscited by 48
  33. 2021Text-to-Table: A New Way of Information Extractioncited by 47
  34. 2020Logic2Text: High-Fidelity Natural Language Generation from Logical Formscited by 45
  35. 2023ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systemscited by 45
  36. 2021Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Datacited by 43
  37. 2023Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Tablecited by 40
  38. 2023Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queriescited by 38

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 5.

10 papers.

  1. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 16
  2. 2025Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoningcited by 10
  3. 2025TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understandingcited by 3
  4. 2026TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detectioncited by 1
  5. 2025LLM-Based Instance-Driven Heuristic Bias In the Context of a Biased Random Key Genetic Algorithmcited by 0
  6. 2025Debugging Tabular Log as Dynamic Graphscited by 0
  7. 2026SciTaRC: A Plan-Annotated Scientific Tabular QA Benchmark for Language Reasoning and Complex Computationcited by 0
  8. 2026ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answeringcited by 0
  9. 2026Large language model-enabled automated data extraction for concrete materials informaticscited by 0
  10. 2026Creation begins with understanding: LLMs as strategy designers for privacy-preserving tabular data synthesiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Rethinking Tabular Data Understanding with Large Language Models
  2. 2024Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding
  3. 2026A Closer Look into LLMs for Table Understanding
  4. 2025How well do LLMs reason over tabular data, really?
  5. 2025RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis
  6. 2025Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data
  7. 2025Improving Table Understanding with LLMs and Entity-Oriented Search
  8. 2025Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System