mlsanityData to 7 Oct 2026

Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples

arXiv 2307.14565 ↗First posted 27 Jul 2023cs.DB cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Relational tables, where each row corresponds to an entity and each column corresponds to an attribute, have been the standard for tables in relational databases. However, such a standard cannot be taken for granted when dealing with tables "in the wild". Our survey of real spreadsheet-tables and web-tables shows that over 30% of such tables do not conform to the relational standard, for which complex table-restructuring transformations are needed before these tables can be queried easily using SQL-based analytics tools. Unfortunately, the required transformations are non-trivial to program, which has become a substantial pain point for technical and non-technical users alike, as evidenced by large numbers of forum questions in places like StackOverflow and Excel/Power-BI/Tableau forums. We develop an Auto-Tables system that can automatically synthesize pipelines with multi-step transformations (in Python or other languages), to transform non-relational tables into standard relational forms for downstream analytics, obviating the need for users to manually program transformations. We compile an extensive benchmark for this new task, by collecting 244 real test cases from user spreadsheets and online forums. Our evaluation suggests that Auto-Tables can successfully synthesize transformations for over 70% of test cases at interactive speeds, without requiring any input from users, making this an effective tool for both technical and non-technical users to prepare data for analytics.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 21 of its 79 references that are in the map. First posted on arXiv 27 Jul 2023.

Builds on

21 of 79 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2020Scaling Laws for Neural Language Modelscited by 6,411
  7. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  8. 2016Enriching Word Vectors with Subword Informationcited by 1,578
  9. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  10. 2020A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospectscited by 396
  11. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  12. 2022Can Foundation Models Wrangle Your Data?cited by 173
9 more
  1. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  2. 2021TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Datacited by 36
  3. 2021Auto-FuzzyJoin: Auto-Program Fuzzy Similarity Joins Without Labeled Examplescited by 15
  4. 2021Lux: Always-on Visualization Recommendations for Exploratory Dataframe Workflowscited by 10
  5. 2021Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Searchcited by 8
  6. 2023Auto-BI: Automatically Build BI-Models Leveraging Local Join Prediction and Global Schema Graphcited by 7
  7. 2017Navigating the Data Lake with Datamaran: Automatically Extracting Structure from Log Datasetscited by 5
  8. 2020PATSQL: Efficient Synthesis of SQL Queries from Example Tables with Quick Inference of Projected Columnscited by 4
  9. 2021Efficiently Transforming Tables for Joinabilitycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 10; 2026: 2.

15 papers.

Sort:

By area:

  1. 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Sciencecited by 49
  2. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 15
  3. 2025MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmarkcited by 13
  4. 2024Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representationscited by 12
  5. 2024AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Frameworkcited by 12
  6. 2025Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflowscited by 9
  7. 2024Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuningcited by 7
  8. 2025Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelinescited by 5
  9. 2025Interactive Data Harmonization with LLM Agents: Opportunities and Challengescited by 3
  10. 2025Empowering Tabular Data Preparation with Language Models: Why and How?cited by 3
  11. 2025Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nestingcited by 1
  12. 2025HCT-QA: A Benchmark for Question Answering on Human-Centric Tablescited by 1
3 more
  1. 2025MontePrep: Monte-Carlo-Driven Automatic Data Preparation without Target Data Instancescited by 1
  2. 2026QUIETT: Query-Independent Table Transformation for Robust Reasoningcited by 0
  3. 2026BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligencecited by 0