Novel Preprocessing Technique for Data Embedding in Engineering Code Generation Using Large Language Model

TL;DR

This paper introduces innovative data preprocessing and verification techniques to improve large language models' ability to generate accurate, domain-specific engineering code, demonstrated through a case study with RedHawk-SC software.

Contribution

The paper presents new LLM-based data splitting, renovation, and verification methods, along with a prompt technique, to enhance domain-specific code generation performance.

Findings

Achieved 73.33% correct lines in MapReduce code generation

Enhanced retrieval relevance with IKEC and RAG techniques

Demonstrated effectiveness in engineering simulation software context

Abstract

We present four main contributions to enhance the performance of Large Language Models (LLMs) in generating domain-specific code: (i) utilizing LLM-based data splitting and data renovation techniques to improve the semantic representation of embeddings' space; (ii) introducing the Chain of Density for Renovation Credibility (CoDRC), driven by LLMs, and the Adaptive Text Renovation (ATR) algorithm for assessing data renovation reliability; (iii) developing the Implicit Knowledge Expansion and Contemplation (IKEC) Prompt technique; and (iv) effectively refactoring existing scripts to generate new and high-quality scripts with LLMs. By using engineering simulation software RedHawk-SC as a case study, we demonstrate the effectiveness of our data pre-processing method for expanding and categorizing scripts. When combined with IKEC, these techniques enhance the Retrieval-Augmented Generation (RAG) method in retrieving more relevant information, ultimately achieving a 73.33% "Percentage of Correct Lines" for code generation problems in MapReduce applications.