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

arXiv: https://arxiv.org/abs/2303.10138 · HTML: https://mlsanity.com/paper/2303.10138/

## 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 (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://mlsanity.com/paper/2201.05966/) (2022)
- [Unsupervised Quality Estimation for Neural Machine Translation](https://mlsanity.com/paper/2005.10608/) (2020)
- [TALM: Tool Augmented Language Models](https://mlsanity.com/paper/2205.12255/) (2022)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022)
- [Coarse-to-Fine Decoding for Neural Semantic Parsing](https://mlsanity.com/paper/1805.04793/) (2018)
- [Learning to Execute](https://mlsanity.com/paper/1410.4615/) (2014)
- [On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries](https://mlsanity.com/paper/2010.11246/) (2020)
- [Neural Programmer: Inducing Latent Programs with Gradient Descent](https://mlsanity.com/paper/1511.04834/) (2015)
- [OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering](https://mlsanity.com/paper/2207.03637/) (2022)
- [Naver Labs Europe's Systems for the WMT19 Machine Translation Robustness Task](https://mlsanity.com/paper/1907.06488/) (2019)

## Built on by (most cited first, 11 of 11)

- [FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering](https://mlsanity.com/paper/2405.13873/) (2024)
- [TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning](https://mlsanity.com/paper/2312.09039/) (2023)
- [Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources](https://mlsanity.com/paper/2409.08239/) (2024)
- [Effective Distillation of Table-based Reasoning Ability from LLMs](https://mlsanity.com/paper/2309.13182/) (2023)
- [TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data](https://mlsanity.com/paper/2401.13223/) (2024)
- [Investigating Table-to-Text Generation Capabilities of LLMs in Real-World Information Seeking Scenarios](https://mlsanity.com/paper/2305.14987/) (2023)
- [From Words to Code: Harnessing Data for Program Synthesis from Natural Language](https://mlsanity.com/paper/2305.01598/) (2023)
- [On Evaluating the Integration of Reasoning and Action in LLM Agents with Database Question Answering](https://mlsanity.com/paper/2311.09721/) (2023)
- [Solving Data-centric Tasks using Large Language Models](https://mlsanity.com/paper/2402.11734/) (2024)
- [Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence](https://mlsanity.com/paper/2507.10281/) (2025)
- [AILS-NTUA at SemEval-2025 Task 8: Language-to-Code prompting and Error Fixing for Tabular Question Answering](https://mlsanity.com/paper/2503.00435/) (2025)

## 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.