# MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering

arXiv: https://arxiv.org/abs/2305.12820 · HTML: https://mlsanity.com/paper/2305.12820/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 22 May 2023.

## Builds on (most cited first, 30 of 30)

- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [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)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [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)
- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing](https://mlsanity.com/paper/2009.13845/) (2020)
- [Investigating the Limitations of Transformers with Simple Arithmetic Tasks](https://mlsanity.com/paper/2102.13019/) (2021)
- [HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation](https://mlsanity.com/paper/2108.06712/) (2021)
- [KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers](https://mlsanity.com/paper/2106.11455/) (2021)
- [Learning a Neural Semantic Parser from User Feedback](https://mlsanity.com/paper/1704.08760/) (2017)
- [On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries](https://mlsanity.com/paper/2010.11246/) (2020)
- [MATE: Multi-view Attention for Table Transformer Efficiency](https://mlsanity.com/paper/2109.04312/) (2021)
- [Text-to-Table: A New Way of Information Extraction](https://mlsanity.com/paper/2109.02707/) (2021)
- [A Survey on Table Question Answering: Recent Advances](https://mlsanity.com/paper/2207.05270/) (2022)
- [PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training](https://mlsanity.com/paper/2211.02816/) (2022)
- [Open Domain Question Answering with A Unified Knowledge Interface](https://mlsanity.com/paper/2110.08417/) (2021)
- [Table-To-Text generation and pre-training with TabT5](https://mlsanity.com/paper/2210.09162/) (2022)
- [Summarizing and Exploring Tabular Data in Conversational Search](https://mlsanity.com/paper/2005.11490/) (2020)
- [FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining](https://mlsanity.com/paper/2109.07323/) (2021)
- [TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data](https://mlsanity.com/paper/2205.12682/) (2022)
- [STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing](https://mlsanity.com/paper/2210.11888/) (2022)
- [Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model](https://mlsanity.com/paper/2109.04672/) (2021)
- [Table-based Fact Verification with Self-adaptive Mixture of Experts](https://mlsanity.com/paper/2204.08753/) (2022)
- [Parameter-Efficient Abstractive Question Answering over Tables or Text](https://mlsanity.com/paper/2204.03357/) (2022)
- [A Mixed Hierarchical Attention based Encoder-Decoder Approach for Standard Table Summarization](https://mlsanity.com/paper/1804.07790/) (2018)
- [Enhancing Tabular Reasoning with Pattern Exploiting Training](https://mlsanity.com/paper/2210.12259/) (2022)
- [Leveraging Data Recasting to Enhance Tabular Reasoning](https://mlsanity.com/paper/2211.12641/) (2022)

## Built on by (most cited first, 30 of 32)

- [SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers](https://mlsanity.com/paper/2407.09413/) (2024)
- [BEAVER: An Enterprise Benchmark for Text-to-SQL](https://mlsanity.com/paper/2409.02038/) (2024)
- [TableRAG: Million-Token Table Understanding with Language Models](https://mlsanity.com/paper/2410.04739/) (2024)
- [VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.10704/) (2024)
- [Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks](https://mlsanity.com/paper/2410.01744/) (2024)
- [RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking](https://mlsanity.com/paper/2504.01346/) (2025)
- [TQA-Bench: Evaluating LLMs for Multi-Table Question Answering](https://mlsanity.com/paper/2411.19504/) (2024)
- [On the Noise Robustness of In-Context Learning for Text Generation](https://mlsanity.com/paper/2405.17264/) (2024)
- [AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework](https://mlsanity.com/paper/2412.10422/) (2024)
- [Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges](https://mlsanity.com/paper/2508.00217/) (2025)
- [QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs](https://mlsanity.com/paper/2405.05109/) (2024)
- [Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning](https://mlsanity.com/paper/2505.00016/) (2025)
- [DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections](https://mlsanity.com/paper/2508.15851/) (2025)
- [Table Question Answering for Low-resourced Indic Languages](https://mlsanity.com/paper/2410.03576/) (2024)
- [Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance](https://mlsanity.com/paper/2506.04427/) (2025)
- [Table as a Modality for Large Language Models](https://mlsanity.com/paper/2512.00947/) (2025)
- [TANQ: An open domain dataset of table answered questions](https://mlsanity.com/paper/2405.07765/) (2024)
- [Synthetic SQL Column Descriptions and Their Impact on Text-to-SQL Performance](https://mlsanity.com/paper/2408.04691/) (2024)
- [CoddLLM: Empowering Large Language Models for Data Analytics](https://mlsanity.com/paper/2502.00329/) (2025)
- [Database-Augmented Query Representation for Information Retrieval](https://mlsanity.com/paper/2406.16013/) (2024)
- [Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Models](https://mlsanity.com/paper/2508.09403/) (2025)
- [Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation](https://mlsanity.com/paper/2510.09671/) (2025)
- [RETQA: A Large-Scale Open-Domain Tabular Question Answering Dataset for Real Estate Sector](https://mlsanity.com/paper/2412.10104/) (2024)
- [Generating Tables from the Parametric Knowledge of Language Models](https://mlsanity.com/paper/2406.10922/) (2024)
- [Beyond Natural Language Plans: Structure-Aware Planning for Query-Focused Table Summarization](https://mlsanity.com/paper/2507.22829/) (2025)
- [LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA](https://mlsanity.com/paper/2508.09012/) (2025)
- [TACO: Task-Aware Column Description Generation Using LLMs](https://mlsanity.com/paper/2606.21685/) (2026)
- [Rehearsing Answers to Probable Questions with Perspective-Taking](https://mlsanity.com/paper/2409.18678/) (2024)
- [Benchmarking Table Comprehension In The Wild](https://mlsanity.com/paper/2412.09884/) (2024)
- [UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification](https://mlsanity.com/paper/2505.18122/) (2025)

## Abstract (arXiv)

Recent advances in tabular question answering (QA) with large language models are constrained in their coverage and only answer questions over a single table. However, real-world queries are complex in nature, often over multiple tables in a relational database or web page. Single table questions do not involve common table operations such as set operations, Cartesian products (joins), or nested queries. Furthermore, multi-table operations often result in a tabular output, which necessitates table generation capabilities of tabular QA models. To fill this gap, we propose a new task of answering questions over multiple tables. Our model, MultiTabQA, not only answers questions over multiple tables, but also generalizes to generate tabular answers. To enable effective training, we build a pre-training dataset comprising of 132,645 SQL queries and tabular answers. Further, we evaluate the generated tables by introducing table-specific metrics of varying strictness assessing various levels of granularity of the table structure. MultiTabQA outperforms state-of-the-art single table QA models adapted to a multi-table QA setting by finetuning on three datasets: Spider, Atis and GeoQuery.