# ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning

arXiv: https://arxiv.org/abs/2603.10823 · HTML: https://mlsanity.com/paper/2603.10823/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Privacy-preserving tabular data synthesis, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [Privacy-preserving tabular data synthesis](https://mlsanity.com/synth/privacy-preserving-tabular-data-synthesis/)
- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 30 of 30)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive](https://mlsanity.com/paper/2402.13228/) (2024)
- [Auditing Differentially Private Machine Learning: How Private is Private SGD?](https://mlsanity.com/paper/2006.07709/) (2020)
- [How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models](https://mlsanity.com/paper/2102.08921/) (2021)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [AugGPT: Leveraging ChatGPT for Text Data Augmentation](https://mlsanity.com/paper/2302.13007/) (2023)
- [Reconstruction and Membership Inference Attacks against Generative Models](https://mlsanity.com/paper/1906.03006/) (2019)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Data](https://mlsanity.com/paper/2201.12677/) (2022)
- [CTAB-GAN+: Enhancing Tabular Data Synthesis](https://mlsanity.com/paper/2204.00401/) (2022)
- [TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data](https://mlsanity.com/paper/2211.06550/) (2022)
- [Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes](https://mlsanity.com/paper/2312.12112/) (2023)
- [LLM-powered Data Augmentation for Enhanced Cross-lingual Performance](https://mlsanity.com/paper/2305.14288/) (2023)
- [How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data](https://mlsanity.com/paper/2402.04823/) (2024)
- [AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing](https://mlsanity.com/paper/2310.15479/) (2023)
- [Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models](https://mlsanity.com/paper/2406.13012/) (2024)
- [Privacy Vulnerabilities in Marginals-based Synthetic Data](https://mlsanity.com/paper/2410.05506/) (2024)
- [Utility Theory of Synthetic Data Generation](https://mlsanity.com/paper/2305.10015/) (2023)
- [Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis](https://mlsanity.com/paper/2509.18014/) (2025)
- [SynRL: Aligning Synthetic Clinical Trial Data with Human-preferred Clinical Endpoints Using Reinforcement Learning](https://mlsanity.com/paper/2411.07317/) (2024)

## Built on by (most cited first, 1 of 1)

- [Beyond Distributional Fidelity: Causal-Penalized Diffusion for Synthetic Tabular Data](https://mlsanity.com/paper/2610.11407/) (2026)

## Abstract (arXiv)

Deep generative models can help with data scarcity and privacy by producing synthetic training data, but they struggle in low-data, imbalanced tabular settings to fully learn the complex data distribution. 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), as suggested by recent theoretical analysis. Therefore, we overcome this limitation with ReTabSyn, a Reinforced Tabular Synthesis pipeline that provides direct feedback on feature correlation preservation during synthesizer training. This objective encourages the generator to prioritize the most useful predictive signals when training data is limited, thereby strengthening downstream model utility. 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. Moreover, our approach can be readily extended to control various aspects of synthetic tabular data, such as applying expert-specified constraints on generated observations.