{"total":27,"rows":[{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2310.12746","title":"TabuLa: Harnessing Language Models for Tabular Data Synthesis","created":"2023-10-19","cited_by_count":42,"area":"synth"},{"id":"2406.07217","title":"A Synthetic Dataset for Personal Attribute Inference","created":"2024-06-11","cited_by_count":36,"area":"synth"},{"id":"2402.06806","title":"Systematic Assessment of Tabular Data Synthesis","created":"2024-02-09","cited_by_count":18,"area":"synth"},{"id":"2406.01457","title":"Differentially Private Tabular Data Synthesis using Large Language Models","created":"2024-06-03","cited_by_count":16,"area":"synth"},{"id":"2408.02927","title":"HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection","created":"2024-08-06","cited_by_count":16,"area":"synth"},{"id":"2404.12404","title":"EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models","created":"2024-04-15","cited_by_count":14,"area":"synth"},{"id":"2505.17103","title":"Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation","created":"2025-05-21","cited_by_count":7,"area":"synth"},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2501.16125","title":"SampleLLM: Optimizing Tabular Data Synthesis in Recommendations","created":"2025-01-27","cited_by_count":4,"area":"synth"},{"id":"2503.02152","title":"Tabby: A Language Model Architecture for Tabular and Structured Data Synthesis","created":"2025-03-04","cited_by_count":4,"area":"synth"},{"id":"2509.23041","title":"Virus Infection Attack on LLMs: Your Poisoning Can Spread \"VIA\" Synthetic Data","created":"2025-09-27","cited_by_count":4,"area":"synth"},{"id":"2501.01793","title":"Creating Artificial Students that Never Existed: Leveraging Large Language Models and CTGANs for Synthetic Data Generation","created":"2025-01-03","cited_by_count":3,"area":"synth"},{"id":"2506.19082","title":"FairCauseSyn: Towards Causally Fair LLM-Augmented Synthetic Data Generation","created":"2025-06-23","cited_by_count":3,"area":"synth"},{"id":"2603.10254","title":"Improving TabPFN's Synthetic Data Generation by Integrating Causal Structure","created":"2026-03-10","cited_by_count":3,"area":"synth"},{"id":"2505.22533","title":"TabularQGAN: A quantum generative model for tabular data synthesis","created":"2025-05-28","cited_by_count":2,"area":"synth"},{"id":"2604.23904","title":"Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities","created":"2026-04-26","cited_by_count":2,"area":"synth"},{"id":"2511.00318","title":"A Technical Exploration of Causal Inference with Hybrid LLM Synthetic Data","created":"2025-10-31","cited_by_count":1,"area":"synth"},{"id":"2603.10823","title":"ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning","created":"2026-03-11","cited_by_count":1,"area":"synth"},{"id":"2412.16335","title":"Improving Equity in Health Modeling with GPT4-Turbo Generated Synthetic Data: A Comparative Study","created":"2024-12-20","cited_by_count":0,"area":"synth"},{"id":"2507.10088","title":"Towards High Supervised Learning Utility Training Data Generation: Data Pruning and Column Reordering","created":"2025-07-14","cited_by_count":0,"area":"synth"},{"id":"2507.15839","title":"FASTGEN: Fast and Cost-Effective Synthetic Tabular Data Generation with LLMs","created":"2025-07-21","cited_by_count":0,"area":"synth"},{"id":"2509.20768","title":"Measuring LLM Sensitivity in Transformer-based Tabular Data Synthesis","created":"2025-09-25","cited_by_count":0,"area":"synth"},{"id":"2605.09855","title":"Concordia: Self-Improving Synthetic Tables for Federated LLMs","created":"2026-05-11","cited_by_count":0,"area":"synth"},{"id":"2608.29674","title":"Creation begins with understanding: LLMs as strategy designers for privacy-preserving tabular data synthesis","created":"2026-08-30","cited_by_count":0,"area":"synth"},{"id":"2609.22149","title":"Beyond the Stitching Assumption: A Unified Framework for Multimodal Synthetic Data Evaluation via Semantic Quantization","created":"2026-08-26","cited_by_count":0,"area":"synth"},{"id":"2609.38414","title":"Synthesis Without Training: An Inference-Only Pipeline for Tabular, Temporal, and Relational Synthetic Data","created":"2026-09-29","cited_by_count":0,"area":"synth"}],"next_cursor":null}