Knowledge-Enhanced Program Repair for Data Science Code

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ouyang, Shuyin, Zhang, Jie M., Sun, Zeyu, Penuela, Albert Merono
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916624807755776
author Ouyang, Shuyin
Zhang, Jie M.
Sun, Zeyu
Penuela, Albert Merono
author_facet Ouyang, Shuyin
Zhang, Jie M.
Sun, Zeyu
Penuela, Albert Merono
contents This paper introduces DSrepair, a knowledge-enhanced program repair method designed to repair the buggy code generated by LLMs in the data science domain. DSrepair uses knowledge graph based RAG for API knowledge retrieval as well as bug knowledge enrichment to construct repair prompts for LLMs. Specifically, to enable knowledge graph based API retrieval, we construct DS-KG (Data Science Knowledge Graph) for widely used data science libraries. For bug knowledge enrichment, we employ an abstract syntax tree (AST) to localize errors at the AST node level. DSrepair's effectiveness is evaluated against five state-of-the-art LLM-based repair baselines using four advanced LLMs on the DS-1000 dataset. The results show that DSrepair surpasses all five baselines. Specifically, when compared to the second-best baseline, DSrepair demonstrates significant improvements, fixing 44.4%, 14.2%, 20.6%, and 32.1% more buggy code snippets for each of the four evaluated LLMs, respectively. Additionally, it achieves greater efficiency, reducing the number of tokens required per code task by 17.49%, 34.24%, 24.71%, and 17.59%, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2502_09771
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knowledge-Enhanced Program Repair for Data Science Code
Ouyang, Shuyin
Zhang, Jie M.
Sun, Zeyu
Penuela, Albert Merono
Software Engineering
This paper introduces DSrepair, a knowledge-enhanced program repair method designed to repair the buggy code generated by LLMs in the data science domain. DSrepair uses knowledge graph based RAG for API knowledge retrieval as well as bug knowledge enrichment to construct repair prompts for LLMs. Specifically, to enable knowledge graph based API retrieval, we construct DS-KG (Data Science Knowledge Graph) for widely used data science libraries. For bug knowledge enrichment, we employ an abstract syntax tree (AST) to localize errors at the AST node level. DSrepair's effectiveness is evaluated against five state-of-the-art LLM-based repair baselines using four advanced LLMs on the DS-1000 dataset. The results show that DSrepair surpasses all five baselines. Specifically, when compared to the second-best baseline, DSrepair demonstrates significant improvements, fixing 44.4%, 14.2%, 20.6%, and 32.1% more buggy code snippets for each of the four evaluated LLMs, respectively. Additionally, it achieves greater efficiency, reducing the number of tokens required per code task by 17.49%, 34.24%, 24.71%, and 17.59%, respectively.
title Knowledge-Enhanced Program Repair for Data Science Code
topic Software Engineering
url https://arxiv.org/abs/2502.09771