Knowledge-Enhanced Program Repair for Data Science Code

This paper introduces DSrepair, a knowledge-enhanced program repair approach designed to repair the buggy code generated by LLMs in the data science domain. DSrepair uses knowledge graph based RAG for API knowledge retrieval and bug knowledge enrichment to construct repair prompts for LLMs. Specific...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings / International Conference on Software Engineering S. 898 - 910
Hauptverfasser: Ouyang, Shuyin, Zhang, Jie M., Sun, Zeyu, Penuela, Albert Merono
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 26.04.2025
Schlagworte:
Code Repair
Codes
Computer bugs
Data science
Knowledge Graph
Knowledge graphs
Large Language Model
Large language models
Libraries
Maintenance engineering
Scalability
Software engineering
Syntactics
ISSN:1558-1225
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper introduces DSrepair, a knowledge-enhanced program repair approach designed to repair the buggy code generated by LLMs in the data science domain. DSrepair uses knowledge graph based RAG for API knowledge retrieval and 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. We evaluate DSrepair's effectiveness against five state-of-the-art LLM-based repair baselines using four advanced LLMs on the DS-1000 dataset. The results show that DSrepair outperforms all five baselines. Specifically, when compared to the second-best baseline, DSrepair achieves substantial 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.
ISSN:1558-1225
DOI:10.1109/ICSE55347.2025.00246