Impact-driven Context Filtering For Cross-file Code Completion

TL;DR

This paper introduces CODEFILTER, a novel framework that uses impact-based context filtering to improve repository-level code completion by selecting relevant cross-file contexts, leading to better accuracy and efficiency.

Contribution

The paper proposes an impact-driven filtering method for cross-file code retrieval, significantly enhancing code completion performance and computational efficiency.

Findings

CODEFILTER improves accuracy across benchmarks.

It reduces input prompt length, increasing efficiency.

It generalizes well across different models.

Abstract

Retrieval-augmented generation (RAG) has recently demonstrated considerable potential for repository-level code completion, as it integrates cross-file knowledge with in-file preceding code to provide comprehensive contexts for generation. To better understand the contribution of the retrieved cross-file contexts, we introduce a likelihood-based metric to evaluate the impact of each retrieved code chunk on the completion. Our analysis reveals that, despite retrieving numerous chunks, only a small subset positively contributes to the completion, while some chunks even degrade performance. To address this issue, we leverage this metric to construct a repository-level dataset where each retrieved chunk is labeled as positive, neutral, or negative based on its relevance to the target completion. We then propose an adaptive retrieval context filtering framework, CODEFILTER, trained on this dataset to mitigate the harmful effects of negative retrieved contexts in code completion. Extensive evaluation on the RepoEval and CrossCodeLongEval benchmarks demonstrates that CODEFILTER consistently improves completion accuracy compared to approaches without filtering operations across various tasks. Additionally, CODEFILTER significantly reduces the length of the input prompt, enhancing computational efficiency while exhibiting strong generalizability across different models. These results underscore the potential of CODEFILTER to enhance the accuracy, efficiency, and attributability of repository-level code completion.