arXiv AI October 9, 2026 By Uddipan Basu Bir, Vincent Christlein, Andreas Maier, Mathias Zinnen

From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction

The paper evaluates eight open‑source lightweight Vision‑Language Models (up to 7 B parameters) for converting document images into structured JSON, focusing on heritage collections with historical handwriting and non‑standard layouts. It compares zero‑shot, few‑shot, and fine‑tuned settings, measuring performance with CER, ANLS*, and mAP‑F1, and examines the effects of hyperparameter tuning, image preprocessing, and multi‑stage training. The study demonstrates that adapted VLMs can serve as a sustainable, private alternative to commercial OCR systems for institutional archives.

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 Computation and Language

Sep 30

From Pixels to Pairs: A Comprehensive Benchmark of LLM-Driven Key-Value Extraction in Noisy Document Settings

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

llms computer-vision multimodal benchmarks

arXiv AI

Aug 20

Evaluating Structured Information Extraction with Open Models in a High Risk Public Sector Application

The paper evaluates open-source OCR, LLM, and VLM systems on a high‑risk public sector task: extracting structured data from student application documents. Results show that VLMs generally outperform OCR+LLM pipelines, yet only 4 of 35 configurations achieve F1 scores above 0.5, with most combinations scoring below 0.25. Model size and input quality, especially preserving OCR structure, are critical factors influencing performance.

By Elias Schubert, Felix Bie{\ss}mann

llms computer-vision multimodal benchmarks

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

Aug 24

Identify, Locate, Link: End-to-End Key-Value Extraction from Document Images

arXiv:2608.20868v1 Announce Type: cross Abstract: Document processing pipelines traditionally cascade optical character recognition (OCR) engines with downstream models for structured information ext...

By A. Said Gurbuz (IBM Research Zurich, ETH Zurich), Ahmed Nassar (IBM Research Zurich), Christoph Auer (IBM Research Zurich), Maksym Lysak (IBM Research Zurich), Lucas Morin (IBM Research Zurich), Matteo Omenetti (IBM Research Zurich), Tim Strohmeyer (IBM Research Zurich), Panagiotis Vagenas (IBM Research Zurich), Nikolaos Livathinos (IBM Research Zurich), Michele Dolfi (IBM Research Zurich), Peter Staar (IBM Research Zurich)

llms computer-vision fine-tuning multimodal

arXiv AI

Jul 21

DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth

arXiv:2607. 16203v1 Announce Type: cross Abstract: Document parsing is a foundational step for document understanding tasks such as visual question answering and key information extraction, as it transforms unstructured scanned images into structured representations by extracting textual, visual, and layout information.

By Zihan Xu, Puzhen Wu, Lawrence Chun Man Lau, Wei Liu, Sirui Li, Yifan Peng, Yihao Ding

llms computer-vision nlp multimodal benchmarks safety

Hugging Face Trending Papers

Jul 6

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

We present HunyuanOCR-1. 5, a lightweight end-to-end OCR-specialized vision-language model.

llms agents computer-vision multimodal safety