mlsanityData to 14 Oct 2026

Generate, Transform, Answer: Question Specific Tool Synthesis for Tabular Data

arXiv 2303.10138 ↗First posted 17 Mar 2023cs.LG cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Tabular question answering (TQA) presents a challenging setting for neural systems by requiring joint reasoning of natural language with large amounts of semi-structured data. Unlike humans who use programmatic tools like filters to transform data before processing, language models in TQA process tables directly, resulting in information loss as table size increases. In this paper we propose ToolWriter to generate query specific programs and detect when to apply them to transform tables and align them with the TQA model's capabilities. Focusing ToolWriter to generate row-filtering tools improves the state-of-the-art for WikiTableQuestions and WikiSQL with the most performance gained on long tables. By investigating headroom, our work highlights the broader potential for programmatic tools combined with neural components to manipulate large amounts of structured data.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 32 of its 39 references that are in the map. First posted on arXiv 17 Mar 2023.

Builds on

32 of 39 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  7. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  9. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  10. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  11. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  12. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
20 more
  1. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  2. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  3. 2022PAL: Program-aided Language Modelscited by 652
  4. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  5. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  6. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 398
  7. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 235
  8. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  9. 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 211
  10. 2022TALM: Tool Augmented Language Modelscited by 197
  11. 2020Break It Down: A Question Understanding Benchmarkcited by 131
  12. 2022Large Language Models are few(1)-shot Table Reasonerscited by 116
  13. 2018Coarse-to-Fine Decoding for Neural Semantic Parsingcited by 110
  14. 2014Learning to Executecited by 106
  15. 2020On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queriescited by 60
  16. 2015Neural Programmer: Inducing Latent Programs with Gradient Descentcited by 34
  17. 2022OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answeringcited by 29
  18. 2019Naver Labs Europe's Systems for the WMT19 Machine Translation Robustness Taskcited by 23
  19. 2022Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Modelscited by 10
  20. 2017Neural Semantic Parsing over Multiple Knowledge-basescited by 8

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 4; 2025: 2.

11 papers.

  1. 2024FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answeringcited by 39
  2. 2023TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoningcited by 32
  3. 2024Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sourcescited by 28
  4. 2023Effective Distillation of Table-based Reasoning Ability from LLMscited by 23
  5. 2024TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Datacited by 19
  6. 2023Investigating Table-to-Text Generation Capabilities of LLMs in Real-World Information Seeking Scenarioscited by 12
  7. 2023From Words to Code: Harnessing Data for Program Synthesis from Natural Languagecited by 11
  8. 2023On Evaluating the Integration of Reasoning and Action in LLM Agents with Database Question Answeringcited by 10
  9. 2024Solving Data-centric Tasks using Large Language Modelscited by 2
  10. 2025Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligencecited by 2
  11. 2025AILS-NTUA at SemEval-2025 Task 8: Language-to-Code prompting and Error Fixing for Tabular Question Answeringcited by 0