arXiv AI July 7, 2026 By Nguyen Kim Hai Bui, Md. Easin Arafat, Tam\'as G\'abor Orosz, Mufti Mahmud

When Simpler Is Better: Evaluating Translation Pipelines for Medieval Latin Manuscripts

arXiv:2607. 03836v1 Announce Type: cross Abstract: Despite remarkable progress in machine translation, Vision Language Models (VLMs) struggle on historical manuscripts, a domain that stresses core Natural Language Processing (NLP) capabilities: low-resource transliteration, archaic vocabulary, and noisy input signals.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 13

Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models

arXiv:2605. 16409v3 Announce Type: replace-cross Abstract: Optical character recognition (OCR) and multilingual scene-text understanding remain challenging for multimodal large language models (MLLMs), particularly in real-world images containing small or degraded text, cluttered layouts, occlusion, handwriting, and complex typography.

By Qinwu Xu, Yifan Jiang, Haoyu Ren

llms computer-vision fine-tuning multimodal benchmarks safety

arXiv Computation and Language

Sep 3

MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models

MUDIDI is a two-stage framework designed to digitize multilingual dictionaries that are currently only available as scanned images. The first stage assesses character recognition and markup preservation, while the second stage segments dictionary entries and maps them into the SIL Multi-Dictionary Formatter schema. The authors also release a dataset of 30 annotated dictionaries and benchmark OCR, LLM, and VLM systems, finding that LLMs generally outperform others and that providing additional context improves digitization quality.

By David Setiawan, Temuulen Khishigsuren, Milind Agarwal, Pagnarith Pit, Aso Mahmudi, Ekaterina Vylomova

llms computer-vision nlp multimodal benchmarks

arXiv Machine Learning

Jul 28

When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents

arXiv:2607. 24077v1 Announce Type: cross Abstract: Optical Character Recognition (OCR) is a key component in the digitization of historical archives.

By Marina Gardella (CB), Camilo Mari{\~n}o (UDELAR, CB), Diego Belzarena (UDELAR, CB), Ignacio Ram{\'i}rez (UDELAR), Gregory Randall (UDELAR), Jean-Michel Morel (LU - Hong Kong)

llms computer-vision multimodal benchmarks safety

arXiv Computer Vision

Sep 18

A Free Lunch? Adapting PP-OCRv6 for Historical Text Recognition

The paper adapts the compact PP‑OCRv6 recognizer for historical text recognition and compares it to a conventional CRNN across various training regimes, including generalized pretraining, domain‑specific training, corpus‑level fine‑tuning, and manuscript‑specific few‑shot adaptation on multilingual Latin and Arabic scripts. While PP‑OCRv6 does not always beat the CRNN when trained from scratch, heterogeneous pretraining significantly improves its generalization. Additionally, fine‑tuned PP‑OCRv6 can surpass a large vision‑language model (Qwen3.5‑based Medusa) that is specifically tailored for historical Latin‑script handwriting recognition.

By Benjamin Kiessling (ALMAnaCH)

llms fine-tuning multimodal safety

arXiv AI

Jul 10

ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents

arXiv:2607. 08143v1 Announce Type: cross Abstract: We present the results of HIPE-OCRepair-2026, an ICDAR competition on LLM-assisted OCR post-correction of historical documents.

By Maud Ehrmann, Emanuela Boros, Juri Opitz, Andrianos Michail, Florian Wagner, Simon Clematide

llms computer-vision fine-tuning

arXiv Computer Vision

Sep 1

PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction

arXiv:2606.19096v3 Announce Type: replace Abstract: European Portuguese (pt-PT) is largely absent from Optical Character Recognition (OCR) benchmarks, which skew toward high-resource languages. The f...

By Jo\~ao Cardeira, Diogo Gl\'oria-Silva, Manuel Letras da Luz, Rafael Ferreira, Diogo Tavares, David Semedo, Jo\~ao Magalh\~aes

computer-vision benchmarks