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

2024-04-15

AI Summary

To address class imbalance in tabular classification caused by scarcity of minority-class samples, this paper proposes a large language model (LLM)-based synthetic data generation method. Our approach introduces a structured prompting paradigm featuring grouped balanced sample guidance, unified format constraints, and unique variable mapping—integrated with in-context learning (ICL) and explicit tabular semantic modeling—to substantially enhance LLMs’ fidelity and generalizability in minority-class synthesis. Evaluated across multiple real-world tabular datasets, the method achieves state-of-the-art classification performance: average minority-class F1-score improves by 12.6%, while synthesis efficiency is significantly increased. Generated samples pass rigorous statistical similarity tests and demonstrate robust utility in downstream classification tasks, confirming high data quality. This work establishes a reproducible, high-fidelity paradigm for LLM-driven balanced tabular data generation.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

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/

Problem

• Data Imbalance
• Table Data Classification
• Minority Class

Innovation

• EPIC Method
• Synthetic Tabular Data
• Imbalanced Categories