# DISCO-TAB: A Hierarchical Reinforcement Learning Framework for Privacy-Preserving Synthesis of Complex Clinical Data

arXiv: https://arxiv.org/abs/2604.01481 · HTML: https://mlsanity.com/paper/2604.01481/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for clinical treatment and surgery, one of 15 directions in Deep reinforcement learning methods.
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Placed in

- Deep reinforcement learning methods / [RL for clinical treatment and surgery](https://mlsanity.com/deeprl/rl-for-clinical-treatment-and-surgery/)

## Builds on (most cited first, 13 of 13)

- [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)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers](https://mlsanity.com/paper/2302.02041/) (2023)
- [Kamino: Constraint-Aware Differentially Private Data Synthesis](https://mlsanity.com/paper/2012.15713/) (2020)
- [HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection](https://mlsanity.com/paper/2408.02927/) (2024)
- [TableGAN-MCA: Evaluating Membership Collisions of GAN-Synthesized Tabular Data Releasing](https://mlsanity.com/paper/2107.13190/) (2021)
- [AIGT: AI Generative Table Based on Prompt](https://mlsanity.com/paper/2412.18111/) (2024)
- [P-TA: Using Proximal Policy Optimization to Enhance Tabular Data Augmentation via Large Language Models](https://mlsanity.com/paper/2406.11391/) (2024)
- [TAGAL: Tabular Data Generation using Agentic LLM Methods](https://mlsanity.com/paper/2509.04152/) (2025)
- [SynLLM: A Comparative Analysis of Large Language Models for Medical Tabular Synthetic Data Generation via Prompt Engineering](https://mlsanity.com/paper/2508.08529/) (2025)
- [TAEGAN: Generating Synthetic Tabular Data For Data Augmentation](https://mlsanity.com/paper/2410.01933/) (2024)

## Abstract (arXiv)

The development of robust clinical decision support systems is frequently impeded by the scarcity of high-fidelity, privacy-preserving biomedical data. While Generative Large Language Models (LLMs) offer a promising avenue for synthetic data generation, they often struggle to capture the complex, non-linear dependencies and severe class imbalances inherent in Electronic Health Records (EHR), leading to statistically plausible but clinically invalid records. To bridge this gap, we introduce DISCO-TAB (DIScriminator-guided COntrol for TABular synthesis), a novel framework that orchestrates a fine-tuned LLM with a multi-objective discriminator system optimized via Reinforcement Learning. Unlike prior methods relying on scalar feedback, DISCO-TAB evaluates synthesis at four granularities, token, sentence, feature, and row, while integrating Automated Constraint Discovery and Inverse-Frequency Reward Shaping to autonomously preserve latent medical logic and resolve minority-class collapse. We rigorously validate our framework across diverse benchmarks, including high-dimensional, small-sample medical datasets (e.g., Heart Failure, Parkinson's). Our results demonstrate that hierarchical feedback yields state-of-the-art performance, achieving up to 38.2% improvement in downstream clinical classifier utility compared to GAN and Diffusion baselines, while ensuring exceptional statistical fidelity (JSD < 0.01) and robust resistance to membership inference attacks. This work establishes a new standard for generating trustworthy, utility-preserving synthetic tabular data for sensitive healthcare applications.