@inproceedings{hoang-etal-2026-codewiki,
    title = "{C}ode{W}iki: Evaluating {AI}{'}s Ability to Generate Holistic Documentation for Large-Scale Codebases",
    author = "Hoang, Anh Nguyen  and
      Le-Anh, Minh  and
      Le, Bach  and
      Bui, Nghi D. Q.",
    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.288/",
    pages = "5812--5827",
    ISBN = "979-8-89176-395-1",
    abstract = "Comprehensive software documentation is crucial yet costly to produce. Despite recent advances in large language models (LLMs), generating holistic, architecture-aware documentation at the repository level remains challenging due to complex and evolving codebases that exceed LLM context limits. Existing automated methods struggle to capture rich semantic dependencies and architectural structure. We present $\textbf{CodeWiki}$, a unified framework for automated repository-level documentation across seven mainstream programming languages. CodeWiki combines top-down hierarchical decomposition with a divide-and-conquer agent system to preserve architectural context and scale documentation generation, and a bottom-up synthesis that integrates textual descriptions with visual artifacts such as architecture and data-flow diagrams. We also introduce $\textbf{CodeWikiBench}$, a benchmark with hierarchical rubrics and LLM-based evaluation protocols. Experiments show that CodeWiki achieves a 68.79{\%} quality score with proprietary models, outperforming the closed-source DeepWiki baseline by 4.73{\%}, with especially strong gains on scripting languages. CodeWiki is released as open source to support future research."
}