mlsanityData to 7 Oct 2026

Seek and Solve Reasoning for Table Question Answering

arXiv 2409.05286 ↗First posted 9 Sep 2024cs.CL cs.AIcited by 3

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

Abstract (arXiv)

The complexities of table structures and question logic make table-based question answering (TQA) tasks challenging for Large Language Models (LLMs), often requiring task simplification before solving. This paper reveals that the reasoning process during task simplification may be more valuable than the simplified tasks themselves and aims to improve TQA performance by leveraging LLMs' reasoning capabilities. We propose a Seek-and-Solve pipeline that instructs the LLM to first seek relevant information and then answer questions, integrating these two stages at the reasoning level into a coherent Seek-and-Solve Chain of Thought (SS-CoT). Additionally, we distill a single-step TQA-solving prompt from this pipeline, using demonstrations with SS-CoT paths to guide the LLM in solving complex TQA tasks under In-Context Learning settings. Our experiments show that our approaches result in improved performance and reliability while being efficient. Our findings emphasize the importance of eliciting LLMs' reasoning capabilities to handle complex TQA tasks effectively.

Key facts. Cited by 3 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 22 of its 27 references that are in the map. First posted on arXiv 9 Sep 2024.

Builds on

22 of 27 references.

Closest ancestors · 3

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
  3. 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation15 Aug

Other references · 19

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2024Mixtral of Expertscited by 1,785
  7. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  8. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  9. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  10. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 231
  11. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  12. 2022Binding Language Models in Symbolic Languagescited by 224
7 more
  1. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  2. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Datacited by 120
  3. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  4. 2023Large Language Models are Complex Table Parserscited by 28
  5. 2024CABINET: Content Relevance based Noise Reduction for Table Question Answeringcited by 23
  6. 2023Are Human-generated Demonstrations Necessary for In-context Learning?cited by 11
  7. 2024Uncovering Limitations of Large Language Models in Information Seeking from Tablescited by 9

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversalscited by 10
  2. 2025General Table Question Answering via Answer-Formula Joint Generationcited by 7
  3. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2026Accurate Table Question Answering with Accessible LLMs
  2. 2026ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios
  3. 2025Planning for Success: Exploring LLM Long-term Planning Capabilities in Table Understanding
  4. 2025TableReasoner: Advancing Table Reasoning Framework with Large Language Models
  5. 2025Exploring Generative Process Reward Modeling for Semi-Structured Data: A Case Study of Table Question Answering
  6. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering
  7. 2026Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering
  8. 2025SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models