一作ACL 2026Findings· Findings of ACL
H is D oc- OCR : Restoring Visual Grounding in MLLM s for C hinese Historical Document OCR
Jiahuan Cao · Yongxin Shi · Zeyu Shan · Zhengyang Lu · Lianwen Jin
摘要
Chinese historical documents encode millennia of cultural heritage, yet remain largely inaccessible to computational analysis. While multimodal large language models (MLLMs) have achieved strong performance on modern document OCR, their application to historical Chinese texts suffers from severe...