arXiv:2609.00232v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on OCR-centric document understanding and text-rich visual reasoning benchmar...
By Yue Zhou, Yuan Wu, Yi Chang
arXiv:2608.07742v2 Announce Type: replace
Abstract: Visual-language models (VLMs) frequently struggle with robustness issues in real-world situations due to low- or varying-quality input images. In t...
By Saim Rehman, Muhammad Shafique
arXiv:2608.30678v1 Announce Type: new
Abstract: Text-rich image understanding requires multimodal large language models (MLLMs) to organize OCR (Optical Character Recognition)-grounded evidence acros...
By Gengxu Li, Yuan Wu, Yi Chang
OCR-EDR is a rendering‑aware framework that diagnoses and repairs OCR errors by jointly evaluating an OCR prediction, its editable form, and the rendered image of the source document. It localizes genuine mistakes while preserving valid or rendering‑equivalent predictions, then applies executable edits and iteratively reassesses with updated renderings. On the newly constructed OCRErrBench, the DocEDR model achieves 94.78% diagnostic accuracy and repairs 86.23% of errors, boosting formula metrics by up to 30.99 percentage points and improving CDM scores on several OCR systems.
OCR-EDR is a rendering‑aware framework that diagnoses and repairs OCR errors by comparing an editable OCR prediction with its rendered image. It jointly assesses consistency, localizes genuine errors, and applies executable edits, optionally requesting updated renderings for iterative reassessment. On the newly constructed OCRErrBench, the DocEDR model achieves 94.78% diagnostic accuracy and repairs 86.23% of erroneous inputs, improving formula metrics by up to 30.99 percentage points on benchmark datasets.
By Linnan Zhao, Kang Liu, Hao Yu, Jiabo Zhan, Chong Sun, Chen Li
The paper introduces a controlled benchmark for evaluating large language models (LLMs) on key‑value pair extraction from documents with varying levels of OCR noise. It tests 136 configurations across five instruction‑tuned open‑weight LLMs, three datasets, and four text‑quality conditions, using deterministic decoding to generate 17,688 document‑level inferences. The study finds that clean‑text performance does not reliably predict real‑world robustness, model rankings can reverse under noisy conditions, and few‑shot demonstrations do not always improve accuracy, highlighting reliability risks in OCR‑to‑LLM pipelines.
By Zahra Anvari