AI RESEARCH
FinCriticalED: A Visual Benchmark for Financial Fact-Level OCR
arXiv CS.CV
•
ArXi:2511.14998v3 Announce Type: replace Recent progress in multimodal large language models (MLLMs) has substantially improved document understanding, yet strong optical character recognition (OCR) performance on surface metrics does not guarantee faithful preservation of decision-critical evidence. This limitation is especially consequential in financial documents, where small visual errors can induce discrete shifts in meaning. To study this gap, we Benchmark and dataset details available at.