Self-Improving Tabular Language Models via Iterative Group Alignment

• URL: http://arxiv.org/abs/2604.18966v1
• Date: Tue, 21 Apr 2026 01:29:52 GMT
• Title: Self-Improving Tabular Language Models via Iterative Group Alignment
• Abstract summary: We introduce TabGRAA, the first self-improving framework for data generation via automated feedback.<n>It partitions newly generated samples into high- and low-quality groups, then prioritizes a group-relative advantage objective.<n>Experiments show TabGRAA outperforms existing methods in fidelity, utility, and privacy.
• Score: 76.43372236405664
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While language models have been adapted for tabular data generation, two fundamental limitations remain: (1) static fine-tuning produces models that cannot learn from their own generated samples and adapt to self-correct, and (2) autoregressive objectives preserve local token coherence but neglect global statistical properties, degrading tabular quality. Reinforcement learning offers a potential solution but requires designing reward functions that balance competing objectives -- impractical for tabular data. To fill the gap, we introduce TabGRAA (Tabular Group-Relative Advantage Alignment), the first self-improving framework for tabular data generation via automated feedback. At each iteration, TabGRAA uses an \emph{automated quality signal} -- such as a two-sample distinguishability classifier or a distance-based reward -- to partition newly generated samples into high- and low-quality groups, then optimizes a group-relative advantage objective that reinforces realistic patterns while penalizing artifacts. The specific signal is a modular choice rather than a fixed component of the framework. This establishes a virtuous feedback cycle, where the quality signal is re-computed against newly \emph{generated synthetic} samples at each round; the language model is only fine-tuned on these self-generated signals, so no additional real record is exposed during alignment, mitigating data-leakage risk beyond the initial supervised fine-tuning. Experiments show TabGRAA outperforms existing methods in fidelity, utility, and privacy, while matching or exceeding diffusion-based synthesizers, advancing tabular synthesis from static statistical replication to dynamic, self-improving generation.

Related papers

• Hierarchical Synthetic Tabular Data Generation: A Hybrid Top-Down and Bottom-Up Framework [14.715376615336536]
  We propose a hierarchical hybrid top-down and bottom-up (H-TDBU) framework that decouples semantic structures from texture.<n> Experimental results show that our H-TDBU approach improves train-synthetic-test-real performance over neural baseline methods.<n>Our results suggest that hierarchical rule-guided synthesis provides an effective mechanism for combining controllability, semantic coherence, and statistical fidelity in synthetic data generation.
  arXiv  Detail & Related papers  (2026-05-27T09:21:47Z)
• SEED: Targeted Data Selection by Weighted Independent Set [76.68391670109433]
  We develop a robust and scalable data selection pipeline dubbed SEED.<n>SEED consistently outperforms state-of-the-art methods on instruction tuning, visual instruction tuning, and semantic segmentation.
  arXiv  Detail & Related papers  (2026-05-15T07:26:54Z)
• Provable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs [77.42033827176806]
  One-Shot Federated Learning, where a central server learns a global model in a single communication round, has emerged as a promising paradigm.<n>We propose a novel Federated Model Inversion and Token Relabel framework, which trains the global model by fully exploiting all patches of synthetic images.
  arXiv  Detail & Related papers  (2026-05-11T15:49:08Z)
• Tabular Foundation Model for Generative Modelling [34.3599321018728]
  Generative modelling requires robust, holistic representation learning for a given data modality, rather than optimisation for a supervised prediction target alone.<n>Existing tabular foundation generators have not yet consistently matched strong dataset-specific generators in synthetic data quality.<n>We introduce TabFORGE, built on pretrained textbfTabular textbfFOundational textbfRepresentations for textbfGEneration.
  arXiv  Detail & Related papers  (2026-05-10T08:52:28Z)
• Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition [60.52810518437911]
  High-fidelity generative models are increasingly needed in privacy-sensitive scenarios.<n> limited data leads to poor generative models, which in turn fail to mitigate data scarcity.<n>We propose a reinforcement-guided synthetic data generation framework that adapts general-domain generative priors to identity recognition tasks.
  arXiv  Detail & Related papers  (2026-04-09T06:52:03Z)
• ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning [13.307228241887346]
  Deep generative models can help with data scarcity and privacy by producing synthetic training data.<n>We argue that striving for the full joint distribution could be overkill; for greater data efficiency, models should prioritize learning the conditional distribution $P(ymid bmX)$.<n>We empirically fine-tune a language model-based generator using this approach, and across benchmarks with small sample sizes, class imbalance, and distribution shift, ReTabSyn consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-11T14:31:07Z)
• CTTVAE: Latent Space Structuring for Conditional Tabular Data Generation on Imbalanced Datasets [0.0]
  We introduce CTTVAE, a Conditional Transformer-based Tabular Variational Autoencoder equipped with two complementary mechanisms.<n>CTTVAE+TBS consistently yields more representative and utility-aligned samples without destabilizing training.
  arXiv  Detail & Related papers  (2026-02-03T15:25:26Z)
• Modest-Align: Data-Efficient Alignment for Vision-Language Models [67.48633659305592]
  Cross-modal alignment models often suffer from overconfidence and degraded performance when operating in resource-constrained settings.<n>We propose Modest-Align, a lightweight alignment framework designed for robustness and efficiency.<n>Our method offers a practical and scalable solution for cross-modal alignment in real-world, low-resource scenarios.
  arXiv  Detail & Related papers  (2025-10-24T16:11:10Z)
• Efficient Autoregressive Inference for Transformer Probabilistic Models [24.106729589790465]
  We introduce a causal autoregressive buffer that preserves the advantages of both paradigms.<n>A unified training strategy allows seamless integration of set-based and autoregressive modes.<n>Our method matches predictive accuracy of strong baselines while delivering up to 20 times faster joint sampling.
  arXiv  Detail & Related papers  (2025-10-10T15:32:58Z)
• Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes [7.036974567001374]
  ReFine is a framework that guides generation toward domain-specific feature distribution.<n>Experiments on various regression and classification benchmarks demonstrate that ReFine consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-09-12T04:34:46Z)
• SMOTExT: SMOTE meets Large Language Models [19.394116388173885]
  We propose a novel technique, SMOTExT, that adapts the idea of Synthetic Minority Over-sampling (SMOTE) to textual data.<n>Our method generates new synthetic examples by interpolating between BERT-based embeddings of two existing examples.<n>In early experiments, training models solely on generated data achieved comparable performance to models trained on the original dataset.
  arXiv  Detail & Related papers  (2025-05-19T17:57:36Z)
• Fake It Till Make It: Federated Learning with Consensus-Oriented Generation [52.82176415223988]
  We propose federated learning with consensus-oriented generation (FedCOG) FedCOG consists of two key components at the client side: complementary data generation and knowledge-distillation-based model training. Experiments on classical and real-world FL datasets show that FedCOG consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-10T18:49:59Z)
• Self-Supervised Dataset Distillation for Transfer Learning [77.4714995131992]
  We propose a novel problem of distilling an unlabeled dataset into a set of small synthetic samples for efficient self-supervised learning (SSL) We first prove that a gradient of synthetic samples with respect to a SSL objective in naive bilevel optimization is textitbiased due to randomness originating from data augmentations or masking. We empirically validate the effectiveness of our method on various applications involving transfer learning.
  arXiv  Detail & Related papers  (2023-10-10T10:48:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.