作者位次 #2/9ACL 2026Findings· Findings of ACL
Benchmarking Vision-Language Models on C hinese Ancient Documents: From OCR to Knowledge Reasoning
Haiyang Yu · Yuchuan Wu · Fan Shi · Jinghui Lu · Ke Niu · Xiaodong Ge · Minghan Zhuo · Jingqun Tang · Bin Li
摘要
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/...