LLM-based data generation for real-world tabular data can be challenged by the lack of sufficient semantic context in feature names used to describe columns. We hypothesize that enriching prompts with domain-specific insights can improve both the quality and efficiency of data generation. To test this hypothesis, we explore three prompt construction protocols: Expert-guided, LLM-guided, and Novel-Mapping. Through empirical studies with the recently proposed GReaT framework, we find that context-enriched prompts lead to significantly improved data generation quality and training efficiency.
View on arXiv@article{banday2025_2409.03946,
title={ On The Role of Prompt Construction In Enhancing Efficacy and Efficiency of LLM-Based Tabular Data Generation },
author={ Banooqa Banday and Kowshik Thopalli and Tanzima Z. Islam and Jayaraman J. Thiagarajan },
journal={arXiv preprint arXiv:2409.03946},
year={ 2025 }
}