mlsanityData to 7 Oct 2026

Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

arXiv 2401.04398 ↗First posted 9 Jan 2024cs.CLcited by 185

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

Abstract (arXiv)

Table-based reasoning with large language models (LLMs) is a promising direction to tackle many table understanding tasks, such as table-based question answering and fact verification. Compared with generic reasoning, table-based reasoning requires the extraction of underlying semantics from both free-form questions and semi-structured tabular data. Chain-of-Thought and its similar approaches incorporate the reasoning chain in the form of textual context, but it is still an open question how to effectively leverage tabular data in the reasoning chain. We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts. Specifically, we guide LLMs using in-context learning to iteratively generate operations and update the table to represent a tabular reasoning chain. LLMs can therefore dynamically plan the next operation based on the results of the previous ones. This continuous evolution of the table forms a chain, showing the reasoning process for a given tabular problem. The chain carries structured information of the intermediate results, enabling more accurate and reliable predictions. Chain-of-Table achieves new state-of-the-art performance on WikiTQ, FeTaQA, and TabFact benchmarks across multiple LLM choices.

Key facts. Cited by 185 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 37 of its 44 references that are in the map. First posted on arXiv 9 Jan 2024.

Builds on

37 of 44 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning31 Jan
  2. 2022Large Language Models are few(1)-shot Table Reasoners13 Oct

Other references · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  9. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  10. 2023PaLM 2 Technical Reportcited by 1,154
  11. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  12. 2023Reasoning with Language Model is Planning with World Modelcited by 846
23 more
  1. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 710
  2. 2022PAL: Program-aided Language Modelscited by 635
  3. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  4. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  5. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  6. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 425
  7. 2023MathPrompter: Mathematical Reasoning using Large Language Modelscited by 236
  8. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
  9. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  10. 2022Binding Language Models in Symbolic Languagescited by 224
  11. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  12. 2019Handling Divergent Reference Texts when Evaluating Table-to-Text Generationcited by 119
  13. 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
  14. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  15. 2020Understanding tables with intermediate pre-trainingcited by 68
  16. 2020On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queriescited by 59
  17. 2023Tab-CoT: Zero-shot Tabular Chain of Thoughtcited by 42
  18. 2022A Survey on Table Question Answering: Recent Advancescited by 41
  19. 2022PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-trainingcited by 41
  20. 2022OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answeringcited by 29
  21. 2023Benchmarking Large Language Model Capabilities for Conditional Generationcited by 29
  22. 2022Table-To-Text generation and pre-training with TabT5cited by 20
  23. 2023From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuningcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 50; 2025: 94; 2026: 41.

185 papers.

Sort:

By area:

  1. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 428
  2. 2024AFlow: Automating Agentic Workflow Generationcited by 395
  3. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  4. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  5. 2024Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-stepcited by 123
  6. 2024Why Tabular Foundation Models Should Be a Research Prioritycited by 103
  7. 2024Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilizationcited by 97
  8. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 86
  9. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 76
  10. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  11. 2024OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automationcited by 66
  12. 2025Safety in Large Reasoning Models: A Surveycited by 58
38 more
  1. 2025Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generationcited by 57
  2. 2024CRISPR-GPT for Agentic Automation of Gene-editing Experimentscited by 56
  3. 2024Large Language Model for Table Processing: A Surveycited by 52
  4. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMscited by 48
  5. 2024A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Taskscited by 46
  6. 2024TableRAG: Million-Token Table Understanding with Language Modelscited by 40
  7. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decompositioncited by 39
  8. 2025Table-R1: Region-based Reinforcement Learning for Table Understandingcited by 35
  9. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  10. 2024Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extractioncited by 33
  11. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?cited by 30
  12. 2024A Survey of Table Reasoning with Large Language Modelscited by 29
  13. 2025100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Modelscited by 29
  14. 2024LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputationcited by 25
  15. 2024ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Contextcited by 23
  16. 2024AutoDCWorkflow: LLM-based Data Cleaning Workflow Auto-Generation and Benchmarkcited by 23
  17. 2025TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoningcited by 22
  18. 2024Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understandingcited by 20
  19. 2024Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolutioncited by 19
  20. 2025TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoningcited by 19
  21. 2024GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answeringcited by 18
  22. 2024Interpretable LLM-based Table Question Answeringcited by 18
  23. 2025TableMaster: A Recipe to Advance Table Understanding with Language Modelscited by 18
  24. 2024TQA-Bench: Evaluating LLMs for Multi-Table Question Answeringcited by 17
  25. 2025GNNs as Predictors of Agentic Workflow Performancescited by 17
  26. 2025RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarkingcited by 17
  27. 2024NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalizationcited by 16
  28. 2025TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answeringcited by 14
  29. 2025Multimodal Tabular Reasoning with Privileged Structured Informationcited by 14
  30. 2024PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tablescited by 13
  31. 2024Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answeringcited by 13
  32. 2024Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science with Table-Specific Pretrainingcited by 12
  33. 2024AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Frameworkcited by 12
  34. 2025HyperG: Hypergraph-Enhanced LLMs for Structured Knowledgecited by 11
  35. 2025HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systemscited by 11
  36. 2024TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoningcited by 10
  37. 2025Effects of Prompt Length on Domain-specific Tasks for Large Language Modelscited by 10
  38. 2025Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answerscited by 10

50 most cited of 185 All 185 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm
  2. 2026Enhancing Table Reasoning with Deterministic Table-State Rewards
  3. 2023TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning
  4. 2026Beyond Linearization: Attributed Table Graphs for Table Reasoning
  5. 2023Rethinking Tabular Data Understanding with Large Language Models
  6. 2022ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples
  7. 2025RUST-BENCH: Benchmarking LLM Reasoning on Unstructured Text within Structured Tables
  8. 2022Reasoning over Hybrid Chain for Table-and-Text Open Domain QA