On The Role of Prompt Construction In Enhancing Efficacy and Efficiency of LLM-Based Tabular Data Generation

Banooqa Banday, Kowshik Thopalli, Tanzima Z. Islam, Jayaraman J. Thiagarajan
9/6/2024
cs.CL

No confident code implementation found for this paper.

Abstract

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 arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

An Automatic Prompt Generation System for Tabular Data Tasks

83% match2024

GReaTER: Generate Realistic Tabular data after data Enhancement and Reduction

82% match2025

TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generation

82% match1 repo42025

Harnessing LLMs Explanations to Boost Surrogate Models in Tabular Data Classification

81% match2025

Examples as the Prompt: A Scalable Approach for Efficient LLM Adaptation in E-Commerce

81% match2025

Large Language Model Prompt Datasets: An In-depth Analysis and Insights

81% match2025

Cite this paper

@article{banday2024role,
  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},
  year   = {2024},
  eprint = {2409.03946},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.03946v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.03946.svg)](https://codeofpaper.com/paper/2409.03946)

Discussion