mlsanityData to 7 Oct 2026

FLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formats

arXiv 2408.08841 ↗First posted 16 Aug 2024cs.CLcited by 8

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

Abstract (arXiv)

The table reasoning task aims to answer the question according to the given table. Currently, using Large Language Models (LLMs) is the predominant method for table reasoning. Most existing methods employ a fixed tabular format to represent the table, which could limit the performance. Given that each instance requires different capabilities and models possess varying abilities, we assert that different instances and models suit different tabular formats. We prove the aforementioned claim through quantitative analysis of experimental results, where different instances and models achieve different performances using various tabular formats. Building on this discussion, we propose FLEXTAF-Single and FLEXTAF-Vote to enhance table reasoning performance by employing flexible tabular formats. Specifically, (i) FLEXTAF-Single trains a classifier to predict the most suitable tabular format based on the instance and the LLM. (ii) FLEXTAF-Vote integrates the results across different formats. Our experiments on WikiTableQuestions and TabFact reveal significant improvements, with average gains of 2.3% and 4.8% compared to the best performance achieved using a fixed tabular format with greedy decoding and self-consistency decoding, thereby validating the effectiveness of our methods.

Key facts. Cited by 8 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 21 of its 58 references that are in the map. First posted on arXiv 16 Aug 2024.

Builds on

21 of 58 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization25 Jun
  2. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition15 Apr
  3. 2024SheetAgent: Towards A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models6 Mar
  4. 2024ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context4 Mar
  5. 2024A Survey of Table Reasoning with Large Language Models13 Feb

Other references · 16

  1. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  2. 2024The Effect of Sampling Temperature on Problem Solving in Large Language Modelscited by 168
  3. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 136
  4. 2024Large Language Models Meet NLP: A Surveycited by 102
  5. 2024Is Temperature the Creativity Parameter of Large Language Models?cited by 92
  6. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 76
  7. 2023Eight Things to Know about Large Language Modelscited by 73
  8. 2024Large Scale Transfer Learning for Tabular Data via Language Modelingcited by 73
  9. 2024Understanding LLMs: A Comprehensive Overview from Training to Inferencecited by 58
  10. 2024Detecting Hallucinations in Large Language Model Generation: A Token Probability Approachcited by 40
  11. 2024SQLBench: A Comprehensive Evaluation for Text-to-SQL Capabilities of Large Language Modelscited by 32
  12. 2024Scaling Trends in Language Model Robustnesscited by 18
4 more
  1. 2024Exploring the Robustness of Language Models for Tabular Question Answering via Attention Analysiscited by 9
  2. 2024Python is Not Always the Best Choice: Embracing Multilingual Program of Thoughtscited by 8
  3. 2023HeLM: Highlighted Evidence augmented Language Model for Enhanced Table-to-Text Generationcited by 4
  4. 2024Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classificationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 2.

8 papers.

  1. 2025RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversalscited by 10
  2. 2025HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimizationcited by 5
  3. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 4
  4. 2025Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligencecited by 2
  5. 2025PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussioncited by 1
  6. 2026TabTracer: Monte Carlo Tree Search for Complex Table Reasoning with Large Language Modelscited by 1
  7. 2025Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Formatcited by 0
  8. 2026How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Locationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Rethinking Tabular Data Understanding with Large Language Models
  2. 2026ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm
  3. 2023TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning
  4. 2026Enhancing Table Reasoning with Deterministic Table-State Rewards
  5. 2024TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning
  6. 2025Multimodal Tabular Reasoning with Privileged Structured Information
  7. 2025TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models
  8. 2025NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables