# StructSynth: Dependency Graphs as Generation Plans for Low-Data Tabular Synthesis with Language Models

arXiv: https://arxiv.org/abs/2508.02601 · HTML: https://mlsanity.com/paper/2508.02601/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 67 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Builds on (most cited first, 26 of 26)

- [Normalizing Flows for Probabilistic Modeling and Inference](https://mlsanity.com/paper/1912.02762/) (2019)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [Generating Multi-label Discrete Patient Records using Generative Adversarial Networks](https://mlsanity.com/paper/1703.06490/) (2017)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [Causal Inference in the Presence of Latent Variables and Selection Bias](https://mlsanity.com/paper/1302.4983/) (2013)
- [DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks](https://mlsanity.com/paper/2110.12884/) (2021)
- [Causal-learn: Causal Discovery in Python](https://mlsanity.com/paper/2307.16405/) (2023)
- [Synthcity: facilitating innovative use cases of synthetic data in different data modalities](https://mlsanity.com/paper/2301.07573/) (2023)
- [Membership Inference Attacks against Synthetic Data through Overfitting Detection](https://mlsanity.com/paper/2302.12580/) (2023)
- [Large Language Model Agent for Hyper-Parameter Optimization](https://mlsanity.com/paper/2402.01881/) (2024)
- [Generative Table Pre-training Empowers Models for Tabular Prediction](https://mlsanity.com/paper/2305.09696/) (2023)
- [Large Language Models for Biomedical Knowledge Graph Construction: Information extraction from EMR notes](https://mlsanity.com/paper/2301.12473/) (2023)
- [Zero-shot Causal Graph Extrapolation from Text via LLMs](https://mlsanity.com/paper/2312.14670/) (2023)
- [Why LLMs Are Bad at Synthetic Table Generation (and what to do about it)](https://mlsanity.com/paper/2406.14541/) (2024)
- [Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting](https://mlsanity.com/paper/2410.01154/) (2024)
- [TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generation](https://mlsanity.com/paper/2502.16414/) (2025)
- [Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs](https://mlsanity.com/paper/2507.19334/) (2025)
- [Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models](https://mlsanity.com/paper/2507.18504/) (2025)
- [AIGT: AI Generative Table Based on Prompt](https://mlsanity.com/paper/2412.18111/) (2024)
- [GraphOracle: Efficient Fully-Inductive Knowledge Graph Reasoning via Relation-Dependency Graphs](https://mlsanity.com/paper/2505.11125/) (2025)
- [Fairness-Driven LLM-based Causal Discovery with Active Learning and Dynamic Scoring](https://mlsanity.com/paper/2503.17569/) (2025)

## Abstract (arXiv)

Tabular data derives its value from inter-feature dependencies, yet preserving them during synthesis is fragile when samples are scarce. Existing approaches either learn dependencies implicitly through distribution fitting, rely on statistical graph learning that becomes unstable with few samples, or encode structure through flat text serialization. Recent graph-aware methods use dependency graphs as attention biases or as backbones for non-LLM samplers, but they do not use the graph as a prompt-level plan for organizing the LLM's own generation process. We introduce StructSynth, a framework that treats a dependency graph as a generation plan---determining the generation order, conditioning context, and scope of each black-box LLM call. In Evidence-Grounded Graph Induction, LLM reasoning and statistical association cues jointly construct a Directed Acyclic Graph (DAG) from limited samples. In Graph-Planned Conditional Synthesis, this DAG drives autoregressive synthesis in topological order, conditioning each feature on previously generated values with graph-specified parent structure guiding each step, making the conditioning schedule explicit throughout synthesis. Experiments show that StructSynth achieves state-of-the-art downstream utility and the best privacy-risk ranking among fourteen compared generators in low-data settings.