Automatic Data Transformation Using Large Language Model: An Experimental Study on Building Energy Data

TL;DR

This paper introduces SQLMorpher, an LLM-based framework for automatic data transformation in building energy datasets, achieving high accuracy and reducing domain knowledge barriers.

Contribution

It pioneers an end-to-end LLM-based approach for data transformation, including a benchmark dataset and extensive empirical evaluation.

Findings

Achieved 96% accuracy on 105 real-world problems

Demonstrated effectiveness of LLMs in complex domain-specific data transformation

Developed an iterative prompt optimization mechanism

Abstract

Existing approaches to automatic data transformation are insufficient to meet the requirements in many real-world scenarios, such as the building sector. First, there is no convenient interface for domain experts to provide domain knowledge easily. Second, they require significant training data collection overheads. Third, the accuracy suffers from complicated schema changes. To bridge this gap, we present a novel approach that leverages the unique capabilities of large language models (LLMs) in coding, complex reasoning, and zero-shot learning to generate SQL code that transforms the source datasets into the target datasets. We demonstrate the viability of this approach by designing an LLM-based framework, termed SQLMorpher, which comprises a prompt generator that integrates the initial prompt with optional domain knowledge and historical patterns in external databases. It also implements an iterative prompt optimization mechanism that automatically improves the prompt based on flaw detection. The key contributions of this work include (1) pioneering an end-to-end LLM-based solution for data transformation, (2) developing a benchmark dataset of 105 real-world building energy data transformation problems, and (3) conducting an extensive empirical evaluation where our approach achieved 96% accuracy in all 105 problems. SQLMorpher demonstrates the effectiveness of utilizing LLMs in complex, domain-specific challenges, highlighting the potential of their potential to drive sustainable solutions.