@inproceedings{huo-etal-2026-reposhapley,
    title = "{R}epo{S}hapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completion",
    author = "Huo, Yu  and
      Zeng, Kun  and
      Zhang, Siyu  and
      LU, Yuquan  and
      Yang, Cheng  and
      Guo, Yifu  and
      Tang, Xiaoying",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.505/",
    pages = "10390--10412",
    ISBN = "979-8-89176-395-1",
    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 offline labeling module, ChunkShapley, estimates signed per-chunk effects via teacher-forced probing, feeds them into a lightweight surrogate game that captures saturation and interference, computes exact Shapley values for small retrieval sets, and selects a decoding-optimal coalition through bounded post-verification with the frozen generator. The verified $<$KEEP$>$ / $<$DROP$>$ decisions and retrieval triggers are then distilled 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."
}