mlsanityData to 14 Oct 2026

API-Assisted Code Generation for Question Answering on Varied Table Structures

arXiv 2310.14687 ↗First posted 23 Oct 2023cs.CL cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

A persistent challenge to table question answering (TableQA) by generating executable programs has been adapting to varied table structures, typically requiring domain-specific logical forms. In response, this paper introduces a unified TableQA framework that: (1) provides a unified representation for structured tables as multi-index Pandas data frames, (2) uses Python as a powerful querying language, and (3) uses few-shot prompting to translate NL questions into Python programs, which are executable on Pandas data frames. Furthermore, to answer complex relational questions with extended program functionality and external knowledge, our framework allows customized APIs that Python programs can call. We experiment with four TableQA datasets that involve tables of different structures -- relational, multi-table, and hierarchical matrix shapes -- and achieve prominent improvements over past state-of-the-art systems. In ablation studies, we (1) show benefits from our multi-index representation and APIs over baselines that use only an LLM, and (2) demonstrate that our approach is modular and can incorporate additional APIs.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 23 Oct 2023.

Builds on

28 of 35 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  4. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  5. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  6. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 603
  7. 2022Visual Programming: Compositional visual reasoning without trainingcited by 516
  8. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  9. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  10. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  11. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  12. 2015Neural Module Networkscited by 376
16 more
  1. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 268
  2. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 235
  3. 2022Binding Language Models in Symbolic Languagescited by 228
  4. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  5. 2017Inferring and Executing Programs for Visual Reasoningcited by 130
  6. 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generationcited by 118
  7. 2016Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervisioncited by 103
  8. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  9. 2016Learning to Compose Neural Networks for Question Answeringcited by 85
  10. 2019Neural Module Networks for Reasoning over Textcited by 66
  11. 2018Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsingcited by 57
  12. 2023Modular Visual Question Answering via Code Generationcited by 48
  13. 2021Capturing Row and Column Semantics in Transformer Based Question Answering over Tablescited by 31
  14. 2021Retrieving Complex Tables with Multi-Granular Graph Representation Learningcited by 24
  15. 2022Table Retrieval May Not Necessitate Table-specific Model Designcited by 11
  16. 2022Full-Text Argumentation Mining on Scientific Publicationscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 6; 2026: 2.

14 papers.

Sort:

By area:

  1. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
  2. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 54
  3. 2024A Survey of Table Reasoning with Large Language Modelscited by 29
  4. 2024PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tablescited by 14
  5. 2024Efficient Prompting for LLM-based Generative Internet of Thingscited by 12
  6. 2024TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoningcited by 10
  7. 2025RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversalscited by 10
  8. 2025General Table Question Answering via Answer-Formula Joint Generationcited by 7
  9. 2025Improved LLM Agents for Financial Document Question Answeringcited by 5
  10. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 5
  11. 2025ITUNLP at SemEval-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using LLM-Driven Code Generationcited by 1
  12. 2025LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QAcited by 1
2 more
  1. 2026DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answeringcited by 0
  2. 2026TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tablescited by 0