RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completion

ACL ARR 2026 January Submission812 Authors

Keywords: Repository-Level Code Completion, Retrieval-Augmented Generation, Large Language Models, Context Filtering

Abstract: Repository-level code completion benefits from retrieval-augmented generation (RAG). However, controlling cross-file evidence is difficult because chunk utility is often interaction-dependent: some snippets help only when paired with complementary context, while others harm decoding when they conflict. We propose RepoShapley, a coalition-aware context filtering framework supervised by Shapley-style marginal contributions. Our module ChunkShapley constructs offline labels by (i) single-chunk probing with teacher-forced likelihood to estimate signed, weighted effects, (ii) a surrogate game that captures saturation and interference, (iii) exact Shapley computation for small retrieval sets, and (iv) bounded post-verification that selects a decoding-optimal coalition using the frozen generator. We distill verified $KEEP$ or $DROP$ decisions and retrieval triggering into a single model via discrete control tokens. Experiments across benchmarks and backbones show that RepoShapley improves completion quality while reducing harmful context and unnecessary retrieval. Code: https://anonymous.4open.science/r/a7f3c9.

Paper Type: Long

Research Area: Code Models

Research Area Keywords: code completion, retrieval-augmented generation, feature attribution, code language models

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: Code

Submission Number: 812