Papers
arxiv:2508.05970

Impact-driven Context Filtering For Cross-file Code Completion

Published on Aug 8
Authors:
,
,
,
,

Abstract

CODEFILTER, an adaptive retrieval context filtering framework, improves repository-level code completion accuracy and efficiency by evaluating and filtering retrieved code chunks.

AI-generated summary

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.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.05970 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2508.05970 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.05970 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.