mlsanityData to 7 Oct 2026

Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning

arXiv 2301.13808 ↗First posted 31 Jan 2023cs.CLcited by 177

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

Abstract (arXiv)

Table-based reasoning has shown remarkable progress in combining deep models with discrete reasoning, which requires reasoning over both free-form natural language (NL) questions and structured tabular data. However, previous table-based reasoning solutions usually suffer from significant performance degradation on huge evidence (tables). In addition, most existing methods struggle to reason over complex questions since the required information is scattered in different places. To alleviate the above challenges, we exploit large language models (LLMs) as decomposers for effective table-based reasoning, which (i) decompose huge evidence (a huge table) into sub-evidence (a small table) to mitigate the interference of useless information for table reasoning; and (ii) decompose complex questions into simpler sub-questions for text reasoning. Specifically, we first use the LLMs to break down the evidence (tables) involved in the current question, retaining the relevant evidence and excluding the remaining irrelevant evidence from the huge table. In addition, we propose a "parsing-execution-filling" strategy to alleviate the hallucination dilemma of the chain of thought by decoupling logic and numerical computation in each step. Extensive experiments show that our method can effectively leverage decomposed evidence and questions and outperforms the strong baselines on TabFact, WikiTableQuestion, and FetaQA datasets. Notably, our model outperforms human performance for the first time on the TabFact dataset.

Key facts. Cited by 177 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 46 of its 61 references that are in the map. First posted on arXiv 31 Jan 2023.

Builds on

46 of 61 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples22 Oct
  2. 2022Large Language Models are few(1)-shot Table Reasoners13 Oct
  3. 2022TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data25 May

Other references · 43

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  7. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  9. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  10. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  11. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  12. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
31 more
  1. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  2. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  3. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  4. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  5. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 425
  6. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  7. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  8. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  9. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  10. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
  11. 2022Binding Language Models in Symbolic Languagescited by 224
  12. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  13. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 166
  14. 2020Unsupervised Question Decomposition for Question Answeringcited by 118
  15. 2022Successive Prompting for Decomposing Complex Questionscited by 94
  16. 2022TableFormer: Robust Transformer Modeling for Table-Text Encodingcited by 90
  17. 2020INFOTABS: Inference on Tables as Semi-structured Datacited by 84
  18. 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 51
  19. 2022Rainier: Reinforced Knowledge Introspector for Commonsense Question Answeringcited by 43
  20. 2022S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parserscited by 41
  21. 2022PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-trainingcited by 41
  22. 2022Two-stage LLM Fine-tuning with Less Specialization and More Generalizationcited by 39
  23. 2022Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsingcited by 30
  24. 2022OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answeringcited by 29
  25. 2020LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Networkcited by 26
  26. 2021Retrieving Complex Tables with Multi-Granular Graph Representation Learningcited by 24
  27. 2021Incorporating External Knowledge to Enhance Tabular Reasoningcited by 23
  28. 2022STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsingcited by 19
  29. 2022Table-based Fact Verification with Self-adaptive Mixture of Expertscited by 12
  30. 2018On-the-fly Table Generationcited by 4
  31. 2020SPot: A tool for identifying operating segments in financial tablescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 24; 2024: 69; 2025: 59; 2026: 25.

177 papers.

Sort:

By area:

  1. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  2. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  3. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 185
  4. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  5. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  6. 2023DocLLM: A layout-aware generative language model for multimodal document understandingcited by 112
  7. 2024Large Language Models Meet NLP: A Surveycited by 102
  8. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  9. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 76
  10. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 69
  11. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  12. 2023Towards Better Chain-of-Thought Prompting Strategies: A Surveycited by 62
38 more
  1. 2024Large Language Model for Table Processing: A Surveycited by 52
  2. 2023SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tablescited by 51
  3. 2024A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Taskscited by 46
  4. 2024TableRAG: Million-Token Table Understanding with Language Modelscited by 40
  5. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decompositioncited by 39
  6. 2023Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queriescited by 38
  7. 2025Table-R1: Region-based Reinforcement Learning for Table Understandingcited by 35
  8. 2023Rethinking Tabular Data Understanding with Large Language Modelscited by 34
  9. 2023Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Datacited by 33
  10. 2023TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoningcited by 32
  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. 2024StructLM: Towards Building Generalist Models for Structured Knowledge Groundingcited by 29
  14. 2024Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoningcited by 27
  15. 2024Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answeringcited by 25
  16. 2024OpenTab: Advancing Large Language Models as Open-domain Table Reasonerscited by 25
  17. 2024LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputationcited by 25
  18. 2024Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planningcited by 24
  19. 2023Effective Distillation of Table-based Reasoning Ability from LLMscited by 23
  20. 2024CABINET: Content Relevance based Noise Reduction for Table Question Answeringcited by 23
  21. 2024ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Contextcited by 23
  22. 2025Large Language Models are Good Relational Learnerscited by 22
  23. 2025TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoningcited by 22
  24. 2024Atomic Fact Decomposition Helps Attributed Question Answeringcited by 21
  25. 2024Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understandingcited by 20
  26. 2023Robust Prompt Optimization for Large Language Models Against Distribution Shiftscited by 19
  27. 2024TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Datacited by 19
  28. 2024Transforming Wearable Data into Personal Health Insights using Large Language Model Agentscited by 19
  29. 2024Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolutioncited by 19
  30. 2023MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Imagescited by 18
  31. 2024Interpretable LLM-based Table Question Answeringcited by 18
  32. 2025TableMaster: A Recipe to Advance Table Understanding with Language Modelscited by 18
  33. 2023Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoningcited by 16
  34. 2024SheetAgent: Towards A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Modelscited by 16
  35. 2024NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalizationcited by 16
  36. 2023Iterative Forward Tuning Boosts In-Context Learning in Language Modelscited by 15
  37. 2023From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuningcited by 14
  38. 2024FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answeringcited by 14

50 most cited of 177 All 177 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding
  2. 2025Efficient Inference for Large Reasoning Models: A Survey
  3. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  4. 2026CRAFT: A Unified Counterfactual Reasoning Framework for Tabular Question Answering and Fact Verification
  5. 2022Faithful Reasoning Using Large Language Models
  6. 2026DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL
  7. 2026ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios
  8. 2025TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models