mlsanityData to 7 Oct 2026

REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers

arXiv 2302.02041 ↗First posted 4 Feb 2023cs.LGcited by 93

Not on the map. Why?

Abstract (arXiv)

Tabular data is a common form of organizing data. Multiple models are available to generate synthetic tabular datasets where observations are independent, but few have the ability to produce relational datasets. Modeling relational data is challenging as it requires modeling both a "parent" table and its relationships across tables. We introduce REaLTabFormer (Realistic Relational and Tabular Transformer), a tabular and relational synthetic data generation model. It first creates a parent table using an autoregressive GPT-2 model, then generates the relational dataset conditioned on the parent table using a sequence-to-sequence (Seq2Seq) model. We implement target masking to prevent data copying and propose the Qδ statistic and statistical bootstrapping to detect overfitting. Experiments using real-world datasets show that REaLTabFormer captures the relational structure better than a baseline model. REaLTabFormer also achieves state-of-the-art results on prediction tasks, "out-of-the-box", for large non-relational datasets without needing fine-tuning.

Key facts. Cited by 93 papers in the map (data through 7 Oct 2026). Builds on 20 of its 44 references that are in the map. First posted on arXiv 4 Feb 2023.

Builds on

20 of 44 references.

References · 20

  1. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  2. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  3. 2023Extracting Training Data from Diffusion Modelscited by 723
  4. 2019Modeling Tabular data using Conditional GANcited by 695
  5. 2021Tabular Data: Deep Learning is Not All You Needcited by 530
  6. 2019Are Transformers universal approximators of sequence-to-sequence functions?cited by 404
  7. 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
  8. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
  9. 2022Language Models are Realistic Tabular Data Generatorscited by 290
  10. 2018Data Synthesis based on Generative Adversarial Networkscited by 184
  11. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  12. 2020Tabular Transformers for Modeling Multivariate Time Seriescited by 77
8 more
  1. 2019Macro F1 and Macro F1cited by 70
  2. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  3. 2014Differential Privacy and Machine Learning: a Survey and Reviewcited by 66
  4. 2020A Non-Parametric Test to Detect Data-Copying in Generative Modelscited by 52
  5. 2022Row Conditional-TGAN for generating synthetic relational databasescited by 15
  6. 2018Deep learning for comprehensive forecasting of Alzheimer's Disease progressioncited by 11
  7. 2021Synthesising Multi-Modal Minority Samples for Tabular Datacited by 10
  8. 2015A review of homomorphic encryption and software tools for encrypted statistical machine learningcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 21; 2025: 36; 2026: 27.

93 papers.

Sort:

By area:

  1. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  2. 2023TabuLa: Harnessing Language Models for Tabular Data Synthesiscited by 42
  3. 2023TabMT: Generating tabular data with masked transformerscited by 36
  4. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 27
  5. 2024TabPFGen -- Tabular Data Generation with TabPFNcited by 26
  6. 2024Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolutioncited by 19
  7. 2024Systematic Assessment of Tabular Data Synthesiscited by 17
  8. 2024HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protectioncited by 16
  9. 2025TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fieldscited by 15
  10. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 15
  11. 2026PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Modelscited by 15
  12. 2023The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasetscited by 14
38 more
  1. 2025TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Datacited by 13
  2. 2025A Case Study Exploring the Current Landscape of Synthetic Medical Record Generation with Commercial LLMscited by 13
  3. 2023One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Datacited by 12
  4. 2024Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Modelscited by 12
  5. 2025TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generationcited by 10
  6. 2024Why LLMs Are Bad at Synthetic Table Generation (and what to do about it)cited by 9
  7. 2024Navigating Tabular Data Synthesis Research: Understanding User Needs and Tool Capabilitiescited by 8
  8. 2025LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusioncited by 8
  9. 2024MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Datacited by 7
  10. 2024LaTable: Towards Large Tabular Modelscited by 7
  11. 2024Benchmarking the Fidelity and Utility of Synthetic Relational Datacited by 7
  12. 2023GeoFormer: Predicting Human Mobility using Generative Pre-trained Transformer (GPT)cited by 5
  13. 2024Improve Fidelity and Utility of Synthetic Credit Card Transaction Time Series from Data-centric Perspectivecited by 5
  14. 2025Privacy Auditing Synthetic Data Release through Local Likelihood Attackscited by 5
  15. 2026A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Datacited by 5
  16. 2023Privacy Measurement in Tabular Synthetic Data: State of the Art and Future Research Directionscited by 4
  17. 2024Synthetic Data from Diffusion Models Improve Drug Discovery Predictioncited by 4
  18. 2024Preserving logical and functional dependencies in synthetic tabular datacited by 4
  19. 2024A text-to-tabular approach to generate synthetic patient data using LLMscited by 4
  20. 2025SampleLLM: Optimizing Tabular Data Synthesis in Recommendationscited by 4
  21. 2025Tabby: A Language Model Architecture for Tabular and Structured Data Synthesiscited by 4
  22. 2025Generative Active Adaptation for Drifting and Imbalanced Network Intrusion Detectioncited by 4
  23. 2025Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Aheadcited by 4
  24. 2025Diffusion Transformers for Tabular Data Time Series Generationcited by 4
  25. 2025Ensembling Membership Inference Attacks Against Tabular Generative Modelscited by 4
  26. 2025Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesiscited by 4
  27. 2023When Synthetic Data Met Regulationcited by 3
  28. 2024iTBLS: A Dataset of Interactive Conversations Over Tabular Informationcited by 3
  29. 2025GReaTER: Generate Realistic Tabular data after data Enhancement and Reductioncited by 3
  30. 2025Graph-Conditional Flow Matching for Relational Data Generationcited by 3
  31. 2025RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Modelscited by 3
  32. 2025FairCauseSyn: Towards Causally Fair LLM-Augmented Synthetic Data Generationcited by 3
  33. 2025When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generationcited by 3
  34. 2023IRG: Modular Synthetic Relational Database Generation with Complex Relational Schemascited by 2
  35. 2024DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Roomcited by 2
  36. 2025TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformercited by 2
  37. 2025Contrastive Learning-Based privacy metrics in Tabular Synthetic Datasetscited by 2
  38. 2025Dependency-aware synthetic tabular data generationcited by 2

50 most cited of 93 All 93 (JSON)