# SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA arXiv: https://arxiv.org/abs/2409.16682 ยท HTML: https://mlsanity.com/paper/2409.16682/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Builds on 35 of its 45 references that are in the map. - First posted on arXiv 25 Sep 2024. ## Builds on (most cited first, 30 of 35) - [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019) - [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020) - [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) - [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023) - [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020) - [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019) - [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021) - [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021) - [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023) - [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020) - [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021) - [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022) - [Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation](https://mlsanity.com/paper/1905.08205/) (2019) - [Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models](https://mlsanity.com/paper/2208.03306/) (2022) - [Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning](https://mlsanity.com/paper/2301.13808/) (2023) - [SParC: Cross-Domain Semantic Parsing in Context](https://mlsanity.com/paper/1906.02285/) (2019) - [Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2012.12627/) (2020) - [Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources](https://mlsanity.com/paper/2305.13269/) (2023) - [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022) - [SmBoP: Semi-autoregressive Bottom-up Semantic Parsing](https://mlsanity.com/paper/2010.12412/) (2020) - [Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing](https://mlsanity.com/paper/2301.07507/) (2023) - [Open Domain Question Answering over Tables via Dense Retrieval](https://mlsanity.com/paper/2103.12011/) (2021) - [Table-GPT: Table-tuned GPT for Diverse Table Tasks](https://mlsanity.com/paper/2310.09263/) (2023) - [Understanding tables with intermediate pre-training](https://mlsanity.com/paper/2010.00571/) (2020) - [On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries](https://mlsanity.com/paper/2010.11246/) (2020) - [Scaling Expert Language Models with Unsupervised Domain Discovery](https://mlsanity.com/paper/2303.14177/) (2023) - [Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMs](https://mlsanity.com/paper/2310.10358/) (2023) - [Getting MoRE out of Mixture of Language Model Reasoning Experts](https://mlsanity.com/paper/2305.14628/) (2023) ## Built on by (most cited first, 9 of 9) - [MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering](https://mlsanity.com/paper/2412.15540/) (2024) - [Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration](https://mlsanity.com/paper/2508.15809/) (2025) - [RePanda: Pandas-powered Tabular Verification and Reasoning](https://mlsanity.com/paper/2503.11921/) (2025) - [Improved LLM Agents for Financial Document Question Answering](https://mlsanity.com/paper/2506.08726/) (2025) - [Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning](https://mlsanity.com/paper/2507.20498/) (2025) - [Same Content, Different Representations: A Controlled Study for Table QA](https://mlsanity.com/paper/2509.22983/) (2025) - [Towards Question Answering over Large Semi-structured Tables](https://mlsanity.com/paper/2502.13422/) (2025) - [ITUNLP at SemEval-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using LLM-Driven Code Generation](https://mlsanity.com/paper/2508.00762/) (2025) - [MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering](https://mlsanity.com/paper/2602.09642/) (2026) ## Abstract (arXiv) Text-to-SQL parsing and end-to-end question answering (E2E TQA) are two main approaches for Table-based Question Answering task. Despite success on multiple benchmarks, they have yet to be compared and their synergy remains unexplored. In this paper, we identify different strengths and weaknesses through evaluating state-of-the-art models on benchmark datasets: Text-to-SQL demonstrates superiority in handling questions involving arithmetic operations and long tables; E2E TQA excels in addressing ambiguous questions, non-standard table schema, and complex table contents. To combine both strengths, we propose a Synergistic Table-based Question Answering approach that integrate different models via answer selection, which is agnostic to any model types. Further experiments validate that ensembling models by either feature-based or LLM-based answer selector significantly improves the performance over individual models.