mlsanityData to 7 Oct 2026

Open Question Answering over Tables and Text

arXiv 2010.10439 ↗First posted 20 Oct 2020cs.CL cs.AIcited by 163

Not on the map. Why?

Cited by 27 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In open question answering (QA), the answer to a question is produced by retrieving and then analyzing documents that might contain answers to the question. Most open QA systems have considered only retrieving information from unstructured text. Here we consider for the first time open QA over both tabular and textual data and present a new large-scale dataset Open Table-and-Text Question Answering (OTT-QA) to evaluate performance on this task. Most questions in OTT-QA require multi-hop inference across tabular data and unstructured text, and the evidence required to answer a question can be distributed in different ways over these two types of input, making evidence retrieval challenging -- our baseline model using an iterative retriever and BERT-based reader achieves an exact match score less than 10%. We then propose two novel techniques to address the challenge of retrieving and aggregating evidence for OTT-QA. The first technique is to use "early fusion" to group multiple highly relevant tabular and textual units into a fused block, which provides more context for the retriever to search for. The second technique is to use a cross-block reader to model the cross-dependency between multiple retrieved evidence with global-local sparse attention. Combining these two techniques improves the score significantly, to above 27%.

Key facts. Cited by 163 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 28; 2023: 26; 2024: 35; 2025: 26; 2026: 29.

163 papers.

Sort:

By area:

  1. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
  2. 2022Multimodal Learning with Transformers: A Surveycited by 399
  3. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 347
  4. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  5. 2021MultiModalQA: Complex Question Answering over Text, Tables and Imagescited by 177
  6. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  7. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 166
  8. 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 127
  9. 2022Large Language Models are few(1)-shot Table Reasonerscited by 116
  10. 2024SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulationcited by 100
  11. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 76
  12. 2024SPIQA: A Dataset for Multimodal Question Answering on Scientific Paperscited by 75
38 more
  1. 2021Open Domain Question Answering over Tables via Dense Retrievalcited by 74
  2. 2021MATE: Multi-view Attention for Table Transformer Efficiencycited by 54
  3. 2021Plan-then-Generate: Controlled Data-to-Text Generation via Planningcited by 52
  4. 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Sciencecited by 49
  5. 2022PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Financecited by 45
  6. 2021AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industrycited by 44
  7. 2024Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversationscited by 43
  8. 2024On the Multi-turn Instruction Following for Conversational Web Agentscited by 42
  9. 2024PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makerscited by 42
  10. 2022A Survey on Table Question Answering: Recent Advancescited by 41
  11. 2023Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Tablecited by 40
  12. 2025Representation Learning for Tabular Data: A Comprehensive Surveycited by 36
  13. 2023Rethinking Tabular Data Understanding with Large Language Modelscited by 34
  14. 2024PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answeringcited by 34
  15. 2021Open Domain Question Answering with A Unified Knowledge Interfacecited by 32
  16. 2022HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Datacited by 28
  17. 2023TempTabQA: Temporal Question Answering for Semi-Structured Tablescited by 27
  18. 2024Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrievalcited by 27
  19. 2022Conversational Question Answering on Heterogeneous Sourcescited by 26
  20. 2025Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarkscited by 26
  21. 2021Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answeringcited by 25
  22. 2023IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositionscited by 25
  23. 2024Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answeringcited by 25
  24. 2024OpenTab: Advancing Large Language Models as Open-domain Table Reasonerscited by 25
  25. 2021Retrieving Complex Tables with Multi-Granular Graph Representation Learningcited by 24
  26. 2024Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Datacited by 24
  27. 2024BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebracited by 23
  28. 2021Few-Shot Table-to-Text Generation with Prototype Memorycited by 21
  29. 2021Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approachcited by 20
  30. 2021FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretrainingcited by 19
  31. 2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19
  32. 2024TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Datacited by 19
  33. 2022Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decodercited by 17
  34. 2022Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQAcited by 17
  35. 2023S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answeringcited by 17
  36. 2024TQA-Bench: Evaluating LLMs for Multi-Table Question Answeringcited by 17
  37. 2025TARGET: Benchmarking Table Retrieval for Generative Taskscited by 17
  38. 2022Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledgecited by 14

50 most cited of 163 All 163 (JSON)