mlsanityData to 7 Oct 2026

EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models

arXiv 2404.12404 ↗First posted 15 Apr 2024cs.LG cs.AIcited by 14

On the map: Synthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis

Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable in-context learning capabilities across diverse applications. In this work, we explore the effectiveness of LLMs for generating realistic synthetic tabular data, identifying key prompt design elements to optimize performance. We introduce EPIC, a novel approach that leverages balanced, grouped data samples and consistent formatting with unique variable mapping to guide LLMs in generating accurate synthetic data across all classes, even for imbalanced datasets. Evaluations on real-world datasets show that EPIC achieves state-of-the-art machine learning classification performance, significantly improving generation efficiency. These findings highlight the effectiveness of EPIC for synthetic tabular data generation, particularly in addressing class imbalance. Our source code for our work is available at: https://seharanul17.github.io/project-synthetic-tabular-llm/

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Privacy-preserving tabular data synthesis, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 28 of its 42 references that are in the map. First posted on arXiv 15 Apr 2024.

Builds on

28 of 42 references.

References · 28

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  8. 2023Mistral 7Bcited by 3,065
  9. 2023Large Language Models as Optimizerscited by 830
  10. 2019Modeling Tabular data using Conditional GANcited by 695
  11. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
  12. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 491
16 more
  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  2. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 428
  3. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
  4. 2022Language Models are Realistic Tabular Data Generatorscited by 290
  5. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  6. 2023Large Language Models as General Pattern Machinescited by 196
  7. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  8. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
  9. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structurescited by 108
  10. 2023TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023cited by 73
  11. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  12. 2023Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimescited by 52
  13. 2017Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Recordscited by 36
  14. 2023From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Modelscited by 22
  15. 2021SMOTE-ENC: A novel SMOTE-based method to generate synthetic data for nominal and continuous featurescited by 12
  16. 2022Data transformation based optimized customer churn prediction model for the telecommunication industrycited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 7; 2026: 6.

14 papers.

Sort:

By area:

  1. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 27
  2. 2025A Comprehensive Survey on Imbalanced Data Learningcited by 10
  3. 2024MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Datacited by 7
  4. 2026A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Datacited by 5
  5. 2025TAGAL: Tabular Data Generation using Agentic LLM Methodscited by 3
  6. 2025In-Context Bias Propagation in LLM-Based Tabular Data Generationcited by 1
  7. 2026Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generationcited by 1
  8. 2025A Note on Statistically Accurate Tabular Data Generation Using Large Language Modelscited by 0
  9. 2025Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimescited by 0
  10. 2025Exploring the Heterogeneity of Tabular Data: A Diversity-aware Data Generator via LLMscited by 0
  11. 2026LLM-Driven Performance-Space Augmentation for Meta-Learning-Based Algorithm Selectioncited by 0
  12. 2026BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data Generationcited by 0
2 more
  1. 2026Creation begins with understanding: LLMs as strategy designers for privacy-preserving tabular data synthesiscited by 0
  2. 2026Beyond the Stitching Assumption: A Unified Framework for Multimodal Synthetic Data Evaluation via Semantic Quantizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025FASTGEN: Fast and Cost-Effective Synthetic Tabular Data Generation with LLMs
  2. 2025Tabby: A Language Model Architecture for Tabular and Structured Data Synthesis
  3. 2024A Survey on Data Synthesis and Augmentation for Large Language Models
  4. 2026Why Large Language Models Fail at Tabular Prediction
  5. 2025Scalable In-Context Learning on Tabular Data via Retrieval-Augmented Large Language Models
  6. 2026Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification
  7. 2026Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration
  8. 2025Synthetic Data Generation Using Large Language Models: Advances in Text and Code