mlsanityData to 7 Oct 2026

Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMs

arXiv 2310.10358 ↗First posted 16 Oct 2023cs.CL cs.AIcited by 49

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are increasingly applied for tabular tasks using in-context learning. The prompt representation for a table may play a role in the LLMs ability to process the table. Inspired by prior work, we generate a collection of self-supervised structural tasks (e.g. navigate to a cell and row; transpose the table) and evaluate the performance differences when using 8 formats. In contrast to past work, we introduce 8 noise operations inspired by real-world messy data and adversarial inputs, and show that such operations can impact LLM performance across formats for different structural understanding tasks.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Builds on 10 of its 17 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

10 of 17 references.

References · 10

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  6. 2022Large Language Models are few(1)-shot Table Reasonerscited by 116
  7. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  8. 2023Table-GPT: Table-tuned GPT for Diverse Table Taskscited by 69
  9. 2023TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPTcited by 57
  10. 2021Annotating Columns with Pre-trained Language Modelscited by 37

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 19; 2025: 17; 2026: 12.

49 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  2. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  3. 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 127
  4. 2024Large Language Models Meet NLP: A Surveycited by 102
  5. 2024Large Scale Transfer Learning for Tabular Data via Language Modelingcited by 73
  6. 2024Large Language Model for Table Processing: A Surveycited by 52
  7. 2024A Survey of Table Reasoning with Large Language Modelscited by 29
  8. 2025Large Language Models are Good Relational Learnerscited by 22
  9. 2025TARGET: Benchmarking Table Retrieval for Generative Taskscited by 17
  10. 2023Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Studycited by 14
  11. 2024Tackling prediction tasks in relational databases with LLMscited by 14
  12. 2024LLMs with Industrial Lens: Deciphering the Challenges and Prospects -- A Surveycited by 12
37 more
  1. 2025Retrieval-augmented Large Language Models for Financial Time Series Forecastingcited by 12
  2. 2025RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysiscited by 12
  3. 2025TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generationcited by 10
  4. 2024SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQAcited by 9
  5. 2025NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tablescited by 8
  6. 2025In-context Learning of Evolving Data Streams with Tabular Foundational Modelscited by 7
  7. 2024Data Analysis in the Era of Generative AIcited by 6
  8. 2025HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimizationcited by 5
  9. 2024Vision Language Models for Spreadsheet Understanding: Challenges and Opportunitiescited by 4
  10. 2025TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuningcited by 4
  11. 2026Deep Tabular Research via Continual Experience-Driven Executioncited by 4
  12. 2024iTBLS: A Dataset of Interactive Conversations Over Tabular Informationcited by 3
  13. 2024Generating Tables from the Parametric Knowledge of Language Modelscited by 3
  14. 2024No Size Fits All: The Perils and Pitfalls of Leveraging LLMs Vary with Company Sizecited by 3
  15. 2024Reasoning Factual Knowledge in Structured Data with Large Language Modelscited by 3
  16. 2025Towards Scalable Schema Mapping using Large Language Modelscited by 3
  17. 2025Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMscited by 3
  18. 2025Same Content, Different Representations: A Controlled Study for Table QAcited by 3
  19. 2026ClaimDB: A Fact Verification Benchmark over Large Structured Datacited by 3
  20. 2024Large Language Models are Pattern Matchers: Editing Semi-Structured and Structured Documents with ChatGPTcited by 2
  21. 2025eC-Tab2Text: Aspect-Based Text Generation from e-Commerce Product Tablescited by 2
  22. 2025Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligencecited by 2
  23. 2026Efficient Table Retrieval and Understanding with Multimodal Large Language Modelscited by 2
  24. 2024HySem: A context length optimized LLM pipeline for unstructured tabular extractioncited by 1
  25. 2024Towards More Effective Table-to-Text Generation: Assessing In-Context Learning and Self-Evaluation with Open-Source Modelscited by 1
  26. 2025Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nestingcited by 1
  27. 2026The Effect of Scripts and Formats on LLM Numeracycited by 1
  28. 2026TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answeringcited by 1
  29. 2026TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMscited by 1
  30. 2025Large Language Models for Drug Overdose Prediction from Longitudinal Medical Recordscited by 0
  31. 2025Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classificationcited by 0
  32. 2026How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Locationcited by 0
  33. 2026COACH meets QUORUM: A Framework and Pipeline for Aligning User, Expert and Developer Perspectives in LLM-generated Health Counsellingcited by 0
  34. 2026ZTab: Domain-based Zero-shot Annotation for Table Columnscited by 0
  35. 2026A Closer Look into LLMs for Table Understandingcited by 0
  36. 2026Calibrated Confidence Estimation for Tabular Question Answeringcited by 0
  37. 2026Semantically Similar, Logically Distinct: Diagnosing the Semantic-Answerability Gap in Table RAGcited by 0