CodeRefine: A Pipeline for Enhancing LLM-Generated Code Implementations of Research Papers

TL;DR

CodeRefine is a comprehensive framework that leverages LLMs and structured knowledge extraction to automatically generate and improve code implementations from research papers, bridging the gap between theory and practice.

Contribution

It introduces a multi-step pipeline combining text summarization, knowledge graph creation, and retrieval-augmented generation for more accurate code synthesis from scientific literature.

Findings

Improves code accuracy over zero-shot LLM prompts

Effectively extracts and structures key paper information

Enhances code quality with retrieval-augmented generation

Abstract

This paper presents CodeRefine, a novel framework for automatically transforming research paper methodologies into functional code using Large Language Models (LLMs). Our multi-step approach first extracts and summarizes key text chunks from papers, analyzes their code relevance, and creates a knowledge graph using a predefined ontology. Code is then generated from this structured representation and enhanced through a proposed retrospective retrieval-augmented generation approach. CodeRefine addresses the challenge of bridging theoretical research and practical implementation, offering a more accurate alternative to LLM zero-shot prompting. Evaluations on diverse scientific papers demonstrate CodeRefine's ability to improve code implementation from the paper, potentially accelerating the adoption of cutting-edge algorithms in real-world applications.