mlsanityData to 7 Oct 2026

HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation

arXiv 2108.06712 ↗First posted 15 Aug 2021cs.CL cs.IRcited by 117

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

Abstract (arXiv)

Tables are often created with hierarchies, but existing works on table reasoning mainly focus on flat tables and neglect hierarchical tables. Hierarchical tables challenge existing methods by hierarchical indexing, as well as implicit relationships of calculation and semantics. This work presents HiTab, a free and open dataset to study question answering (QA) and natural language generation (NLG) over hierarchical tables. HiTab is a cross-domain dataset constructed from a wealth of statistical reports (analyses) and Wikipedia pages, and has unique characteristics: (1) nearly all tables are hierarchical, and (2) both target sentences for NLG and questions for QA are revised from original, meaningful, and diverse descriptive sentences authored by analysts and professions of reports. (3) to reveal complex numerical reasoning in statistical analyses, we provide fine-grained annotations of entity and quantity alignment. HiTab provides 10,686 QA pairs and descriptive sentences with well-annotated quantity and entity alignment on 3,597 tables with broad coverage of table hierarchies and numerical reasoning types. Targeting hierarchical structure, we devise a novel hierarchy-aware logical form for symbolic reasoning over tables, which shows high effectiveness. Targeting complex numerical reasoning, we propose partially supervised training given annotations of entity and quantity alignment, which helps models to largely reduce spurious predictions in the QA task. In the NLG task, we find that entity and quantity alignment also helps NLG models to generate better results in a conditional generation setting. Experiment results of state-of-the-art baselines suggest that this dataset presents a strong challenge and a valuable benchmark for future research.

Key facts. Cited by 117 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 35 of its 65 references that are in the map. First posted on arXiv 15 Aug 2021.

Builds on

35 of 65 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  7. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  8. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  9. 2018Annotation Artifacts in Natural Language Inference Datacited by 656
  10. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  11. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  12. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
23 more
  1. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  2. 2018Hypothesis Only Baselines in Natural Language Inferencecited by 291
  3. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
  4. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
  5. 2017Challenges in Data-to-Document Generationcited by 226
  6. 2019Leveraging Pre-trained Checkpoints for Sequence Generation Taskscited by 182
  7. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 144
  8. 2019Handling Divergent Reference Texts when Evaluating Table-to-Text Generationcited by 119
  9. 2016Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervisioncited by 101
  10. 2020Logical Natural Language Generation from Open-Domain Tablescited by 90
  11. 2021Representing Numbers in NLP: a Survey and a Visioncited by 83
  12. 2020On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queriescited by 59
  13. 2018Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsingcited by 57
  14. 2020AxCell: Automatic Extraction of Results from Machine Learning Paperscited by 48
  15. 2020Logic2Text: High-Fidelity Natural Language Generation from Logical Formscited by 45
  16. 2021Retrieving Complex Tables with Multi-Granular Graph Representation Learningcited by 24
  17. 2018End-to-End Content and Plan Selection for Data-to-Text Generationcited by 20
  18. 2021Learning to Reason for Text Generation from Scientific Tablescited by 13
  19. 2021TableSense: Spreadsheet Table Detection with Convolutional Neural Networkscited by 12
  20. 2016Crowd-sourcing NLG Data: Pictures Elicit Better Datacited by 11
  21. 2017Macro Grammars and Holistic Triggering for Efficient Semantic Parsingcited by 10
  22. 2018TabVec: Table Vectors for Classification of Web Tablescited by 8
  23. 2020A Graph Representation of Semi-structured Data for Web Question Answeringcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 10; 2023: 8; 2024: 30; 2025: 45; 2026: 23.

117 papers.

Sort:

By area:

  1. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  2. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 822
  3. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  4. 2024What matters when building vision-language models?cited by 321
  5. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  6. 2024Building and better understanding vision-language models: insights and future directionscited by 169
  7. 2026Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skillscited by 161
  8. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  9. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scalecited by 125
  10. 2024NVLM: Open Frontier-Class Multimodal LLMscited by 124
  11. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Datacited by 120
  12. 2024SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulationcited by 100
38 more
  1. 2024SPIQA: A Dataset for Multimodal Question Answering on Scientific Paperscited by 75
  2. 2024MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuningcited by 75
  3. 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspectivecited by 75
  4. 2024TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Taskscited by 70
  5. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 69
  6. 2024Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Datacited by 61
  7. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 53
  8. 2025FineVision: Open Data Is All You Needcited by 51
  9. 2022Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Taskscited by 42
  10. 2022A Survey on Table Question Answering: Recent Advancescited by 41
  11. 2023RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbationscited by 41
  12. 2022Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learningcited by 32
  13. 2023MultiTabQA: Generating Tabular Answers for Multi-Table Question Answeringcited by 32
  14. 2025SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understandingcited by 30
  15. 2022ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examplescited by 29
  16. 2024A Survey of Table Reasoning with Large Language Modelscited by 29
  17. 2024Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Datacited by 24
  18. 2024CABINET: Content Relevance based Noise Reduction for Table Question Answeringcited by 23
  19. 2021FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretrainingcited by 19
  20. 2022TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Datacited by 19
  21. 2025TableMaster: A Recipe to Advance Table Understanding with Language Modelscited by 18
  22. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  23. 2024TQA-Bench: Evaluating LLMs for Multi-Table Question Answeringcited by 17
  24. 2022PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generationcited by 16
  25. 2024SpreadsheetLLM: Encoding Spreadsheets for Large Language Modelscited by 15
  26. 2023API-Assisted Code Generation for Question Answering on Varied Table Structurescited by 14
  27. 2025Multimodal Tabular Reasoning with Privileged Structured Informationcited by 14
  28. 2024PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tablescited by 13
  29. 2025MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmarkcited by 13
  30. 2023Investigating Table-to-Text Generation Capabilities of LLMs in Real-World Information Seeking Scenarioscited by 12
  31. 2024Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science with Table-Specific Pretrainingcited by 12
  32. 2025RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysiscited by 12
  33. 2022Parameter-Efficient Abstractive Question Answering over Tables or Textcited by 11
  34. 2025Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoningcited by 11
  35. 2023Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Questioncited by 10
  36. 2024cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Paperscited by 10
  37. 2024OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video Understandingcited by 10
  38. 2024TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoningcited by 10

50 most cited of 117 All 117 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024TANQ: An open domain dataset of table answered questions
  2. 2024Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding
  3. 2026PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding
  4. 2026SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables
  5. 2024Text2SQL is Not Enough: Unifying AI and Databases with TAG
  6. 2023Large Language Models are Complex Table Parsers
  7. 2026H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning
  8. 2026Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering