GraphCoder: Enhancing Repository-Level Code Completion via Coarse-to-fine Retrieval Based on Code Context Graph

The performance of repository-level code completion depends upon the effective leverage of both general and repository-specific knowledge. Despite the impressive capability of code LLMs in general code completion tasks, they often exhibit less satisfactory performance on repository-level completion...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE/ACM International Conference on Automated Software Engineering : [proceedings] S. 570 - 581
Hauptverfasser: Liu, Wei, Yu, Ailun, Zan, Daoguang, Shen, Bo, Zhang, Wei, Zhao, Haiyan, Jin, Zhi, Wang, Qianxiang
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: ACM 27.10.2024
Schlagworte:
Accuracy
Code completion
Code graphs
Codes
Computational modeling
Filtering
Information systems
Large language model
Mathematical models
Process control
Retrieval augmented generation
Software
Software algorithms
Software engineering
ISSN:2643-1572
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The performance of repository-level code completion depends upon the effective leverage of both general and repository-specific knowledge. Despite the impressive capability of code LLMs in general code completion tasks, they often exhibit less satisfactory performance on repository-level completion due to the lack of repository-specific knowledge in these LLMs. To address this problem, we propose GraphCoder, a retrieval-augmented code completion framework that leverages LLMs' general code knowledge and the repository-specific knowledge via a graph-based retrieval-generation process. In particular, GraphCoder captures the context of completion target more accurately through code context graph (CCG) that consists of control-flow, data- and control-dependence between code statements, a more structured way to capture the completion target context than the sequence-based context used in existing retrieval-augmented approaches; based on CCG, GraphCoder further employs a coarse-to-fine retrieval process to locate context-similar code snippets with the completion target from the current repository. Experimental results demonstrate both the effectiveness and efficiency of GraphCoder: Compared to baseline retrieval-augmented methods, GraphCoder achieves higher exact match (EM) on average, with increases of +6.06 in code match and +6.23 in identifier match, while using less time and space.CCS Concepts* Software and its engineering → Search-based software engineering; * Information systems → Language models; Query representation; * Mathematics of computing → Graph algorithms.
ISSN:2643-1572
DOI:10.1145/3691620.3695054