@inproceedings{yu-etal-2026-benchmarking,
    title = "Benchmarking Vision-Language Models on {C}hinese Ancient Documents: From {OCR} to Knowledge Reasoning",
    author = "Yu, Haiyang  and
      Wu, Yuchuan  and
      Shi, Fan  and
      Lu, Jinghui  and
      Niu, Ke  and
      Ge, Xiaodong  and
      Zhuo, Minghan  and
      Tang, Jingqun  and
      Li, Bin",
    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.1438/",
    pages = "28793--28812",
    ISBN = "979-8-89176-395-1",
    abstract = "Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and understanding{---}traditional methods only scan images, while current Vision-Language Models (VLMs) struggle with their visual/linguistic complexity. Existing document benchmarks focus on English printed texts or simplified Chinese, leaving a gap for evaluating VLMs on ancient Chinese documents. To address this, we present AncientDoc, the first benchmark for Chinese ancient documents, designed to assess VLMs from OCR to knowledge reasoning. AncientDoc includes five tasks (page-level OCR, vernacular translation, reasoning-based QA, knowledge-based QA, linguistic variant QA) and covers 14 document types, over 100 books, and about 3,000 pages. Based on AncientDoc, we evaluate mainstream VLMs using multiple metrics, supplemented by a human-aligned large language model for scoring."
}