CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Du, Kounianhua, Chen, Jizheng, Rui, Renting, Chai, Huacan, Fu, Lingyue, Xia, Wei, Wang, Yasheng, Tang, Ruiming, Yu, Yong, Zhang, Weinan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910948705435648
author Du, Kounianhua
Chen, Jizheng
Rui, Renting
Chai, Huacan
Fu, Lingyue
Xia, Wei
Wang, Yasheng
Tang, Ruiming
Yu, Yong
Zhang, Weinan
author_facet Du, Kounianhua
Chen, Jizheng
Rui, Renting
Chai, Huacan
Fu, Lingyue
Xia, Wei
Wang, Yasheng
Tang, Ruiming
Yu, Yong
Zhang, Weinan
contents Utilizing large language models to generate codes has shown promising meaning in software development revolution. Despite the intelligence shown by the large language models, their specificity in code generation can still be improved due to the syntactic gap and mismatched vocabulary existing between natural language and programming languages. In this paper, we propose CodeGRAG, a Graphical Retrieval Augmented Code Generation framework that bridges the gap between NL and PL to enhance the performance of LLMs. CodeGRAG builds the graphical view of code blocks based on the control flow and data flow of them to better interpret the programming domain knowledge, which can facilitate natural language based LLMs for better understanding of code syntax and serve as a bridge among different programming languages. To take the extracted structural knowledge into the foundation models, we propose 1) a hard meta-graph prompt template to transform the challenging syntax graph into informative graphical view for tuning-free models and 2) a soft prompting technique that injects the domain knowledge of programming languages into model parameters via finetuning the models with the soft signals encoded by GNN expert model. Specifically, two constraints are designed to improve the alignment and structure expressiveness, contributing to the informativeness of the single-token-sized external <GraphEmb> for enhanced code generation. CodeGRAG significantly improves the code generation ability of LLMs and can even offer performance gain for cross-lingual code generation. Implementation is available at https://anonymous.4open.science/r/Code-5970/ .
format Preprint
id arxiv_https___arxiv_org_abs_2405_02355
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation
Du, Kounianhua
Chen, Jizheng
Rui, Renting
Chai, Huacan
Fu, Lingyue
Xia, Wei
Wang, Yasheng
Tang, Ruiming
Yu, Yong
Zhang, Weinan
Software Engineering
Artificial Intelligence
Utilizing large language models to generate codes has shown promising meaning in software development revolution. Despite the intelligence shown by the large language models, their specificity in code generation can still be improved due to the syntactic gap and mismatched vocabulary existing between natural language and programming languages. In this paper, we propose CodeGRAG, a Graphical Retrieval Augmented Code Generation framework that bridges the gap between NL and PL to enhance the performance of LLMs. CodeGRAG builds the graphical view of code blocks based on the control flow and data flow of them to better interpret the programming domain knowledge, which can facilitate natural language based LLMs for better understanding of code syntax and serve as a bridge among different programming languages. To take the extracted structural knowledge into the foundation models, we propose 1) a hard meta-graph prompt template to transform the challenging syntax graph into informative graphical view for tuning-free models and 2) a soft prompting technique that injects the domain knowledge of programming languages into model parameters via finetuning the models with the soft signals encoded by GNN expert model. Specifically, two constraints are designed to improve the alignment and structure expressiveness, contributing to the informativeness of the single-token-sized external <GraphEmb> for enhanced code generation. CodeGRAG significantly improves the code generation ability of LLMs and can even offer performance gain for cross-lingual code generation. Implementation is available at https://anonymous.4open.science/r/Code-5970/ .
title CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2405.02355