Pith. sign in

REVIEW 21 cited by

Language Models are Realistic Tabular Data Generators

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2210.06280 v2 pith:DN4PKUTH submitted 2022-10-12 cs.LG

Vadim Borisov , Kathrin Se{ss}ler , Tobias Leemann , Martin Pawelczyk , Gjergji Kasneci This is my paper
classification cs.LG
keywords datatabulargenerativegenerationgreatmodelsrealisticsynthetic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Tabular data is among the oldest and most ubiquitous forms of data. However, the generation of synthetic samples with the original data's characteristics remains a significant challenge for tabular data. While many generative models from the computer vision domain, such as variational autoencoders or generative adversarial networks, have been adapted for tabular data generation, less research has been directed towards recent transformer-based large language models (LLMs), which are also generative in nature. To this end, we propose GReaT (Generation of Realistic Tabular data), which exploits an auto-regressive generative LLM to sample synthetic and yet highly realistic tabular data. Furthermore, GReaT can model tabular data distributions by conditioning on any subset of features; the remaining features are sampled without additional overhead. We demonstrate the effectiveness of the proposed approach in a series of experiments that quantify the validity and quality of the produced data samples from multiple angles. We find that GReaT maintains state-of-the-art performance across numerous real-world and synthetic data sets with heterogeneous feature types coming in various sizes.

Discussion (0). Sign in to comment.

Forward citations

Cited by 21 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    ICL in LLMs shows a sharp ceiling on categorical distributions for high-cardinality tabular data, failing to reproduce rare classes despite examples, while numerical fidelity improves.

  2. Concordia: Self-Improving Synthetic Tables for Federated LLMs

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Concordia aligns synthetic table generation with federated validation utility via client-side utility scorers and group-relative policy optimization to improve LLM adaptation on non-IID tabular tasks.

  3. LLM-Driven Performance-Space Augmentation for Meta-Learning-Based Algorithm Selection

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    LLM-generated synthetic datasets steered uniformly across a 2D performance space defined by two landmark algorithms improve meta-learner performance on algorithm selection for regression tasks.

  4. The Power of Order: Fooling LLMs with Adversarial Table Permutations

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Semantically invariant row and column permutations can fool LLMs on tabular tasks, and a new gradient-based attack called ATP finds such permutations to significantly degrade performance across models.

  5. Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training

    cs.LG 2026-04 unverdicted novelty 7.0 of 10

    TabGRAA enables self-improving tabular language models through iterative group-relative advantage alignment using modular automated quality signals like distinguishability classifiers.

  6. AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors

    cs.CV 2026-01 conditional novelty 7.0 of 10

    AnomalyVFM converts vision foundation models into zero-shot anomaly detectors via three-stage synthetic dataset generation plus low-rank adapters and weighted pixel loss, reaching 94.1% average image AUROC across nine...

  7. When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation

    cs.LG 2025-12 conditional novelty 7.0 of 10

    LLM tabular generators leak memorized numeric strings, allowing a no-box attack to achieve near-perfect membership inference on some state-of-the-art models.

  8. FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents

    cs.LG 2026-07 conditional novelty 6.0 of 10

    FairDiffuseVQVAE reaches state-of-the-art fairness on the standard tabular benchmark (DPR 0.702, EOR 0.686) by uniform protected-attribute sampling at inference, paying ~15 AUC points of utility.

  9. Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    DiffICL breaks the quality-privacy tradeoff in small-data tabular synthesis by using in-context learning on pretrained structural priors to generate data that is both higher quality and less memorizing of training samples.

  10. The Power of Order: Fooling LLMs with Adversarial Table Permutations

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Semantically invariant row and column permutations in tables can cause LLMs to output incorrect answers, and a gradient-based attack called ATP efficiently finds such permutations that degrade performance across many models.

  11. From Noise to Order: Learning to Rank via Denoising Diffusion

    cs.IR 2026-02 conditional novelty 6.0 of 10

    DiffusionRank, a diffusion-based generative model over feature-label tuples, improves learning-to-rank over discriminative baselines on MQ2007 and MSLR-WEB10K, but not consistently on MQ2008.

  12. TAGAL: Tabular Data Generation using Agentic LLM Methods

    cs.LG 2025-09 conditional novelty 6.0 of 10

    TAGAL uses an agentic LLM loop, generation plus feedback, to produce synthetic tabular data without LLM training, matching trained models on some datasets and beating the training-free EPIC baseline.

  13. Ensembling Membership Inference Attacks Against Tabular Generative Models

    cs.CR 2025-09 conditional novelty 6.0 of 10

    No single membership inference attack dominates across tabular generative models, and unsupervised ensembles of attacks achieve better average rankings.

  14. Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches

    cs.LG 2025-08 conditional novelty 6.0 of 10

    Serialization format and in-context examples change both accuracy and gender fairness of LLM loan approvals, with finance-tuned models often showing larger disparities.

  15. Meta-learning ecological priors from large language models explains human learning and decision making

    q-bio.NC 2025-08 conditional novelty 6.0 of 10

    A meta-learned transformer trained on LLM-generated tasks (ERMI) outperforms classical cognitive models in predicting human choices across function learning, category learning, and decision making.

  16. Evaluating Inter-Column Logical Relationships in Synthetic Tabular Data Generation

    cs.LG 2025-02 unverdicted novelty 6.0 of 10

    Proposes three metrics for inter-column logical relationships in synthetic tabular data and reports that current generators often fail to preserve them on an industrial dataset.

  17. PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimization

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    PSyGenTAB is a constrained-optimization framework that generates privacy-preserving synthetic clinical tabular data while preserving clinical relationships and downstream model performance.

  18. Concordia: Self-Improving Synthetic Tables for Federated LLMs

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Concordia aligns synthetic table generation with federated validation utility via client-level LoRA training, utility scorers, and outer GRPO refinement to boost performance over static synthetic baselines.

  19. Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training

    cs.LG 2026-04 unverdicted novelty 5.0 of 10

    TabGRAA applies group-relative advantage alignment in an iterative reward-guided post-training loop to improve tabular language model generators on fidelity, utility, and privacy trade-offs across five benchmarks.

  20. A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data

    cs.AI 2026-01 conditional novelty 5.0 of 10

    A metric-oriented survey that classifies intrinsic quality and trustworthiness metrics for LLM-generated data across six modalities and documents systematic evaluation gaps in the current literature.

  21. Creating Artificial Students that Never Existed: Leveraging Large Language Models and CTGANs for Synthetic Data Generation

    cs.LG 2025-01 unverdicted novelty 3.0 of 10

    CTGAN and LLMs generate synthetic student data that passes statistical and predictive utility checks for learning analytics.

Pith tools