Imagen de Portada

Early evidence of how LLMs outperform traditional systems on OCR/HTR tasks for historical records

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kim, Seorin, Baudru, Julien, Ryckbosch, Wouter, Bersini, Hugues, Ginis, Vincent
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DRetHTR: Linear-Time Decoder-Only Retentive Network for Handwritten Text Recognition
por: Kim, Changhun, et al.
Publicado: (2026)

DharmaOCR: Specialized Small Language Models for Structured OCR that outperform Open-Source and Commercial Baselines
por: Cardoso, Gabriel Pimenta de Freitas, et al.
Publicado: (2026)

Combining OCR Models for Reading Early Modern Printed Books
por: Seuret, Mathias, et al.
Publicado: (2023)

MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
por: Shi, Yang, et al.
Publicado: (2025)

HTR-VT: Handwritten Text Recognition with Vision Transformer
por: Li, Yuting, et al.
Publicado: (2024)

Turning Citation Networks Inside Out: Studying Science Using Content-Based Knowledge Graphs from LLM-Derived Taxonomies
por: Kim, Seorin, et al.
Publicado: (2026)

One in Eight OpenAlex Abstracts Has Integrity Issues
por: Kim, Seorin, et al.
Publicado: (2026)

Cross-Language Learning within Arabic Script for Low-Resource HTR
por: Al-azzawi, Sana, et al.
Publicado: (2026)

TRIDIS: A Comprehensive Medieval and Early Modern Corpus for HTR and NER
por: Aguilar, Sergio Torres
Publicado: (2025)

HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge Distillation
por: Hamdan, Mohammed, et al.
Publicado: (2024)

Understanding Cross-Language Transfer Improvements in Low-Resource HTR: The Role of Sequence Modeling
por: Al-azzawi, Sana, et al.
Publicado: (2026)

OCR-Agent: Agentic OCR with Capability and Memory Reflection
por: Wen, Shimin, et al.
Publicado: (2026)

OmniOCR: Generalist OCR for Ethnic Minority Languages
por: Liu, Bonan, et al.
Publicado: (2026)

Context-Independent OCR with Multimodal LLMs: Effects of Image Resolution and Visual Complexity
por: Inoue, Kotaro
Publicado: (2025)

CER-HV: A Human-in-the-Loop Framework for Cleaning Datasets Applied to Arabic-Script HTR
por: Al-azzawi, Sana, et al.
Publicado: (2026)

Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study
por: Fei, Yulin, et al.
Publicado: (2024)

Bridging Human Concepts and Computer Vision for Explainable Face Verification
por: Doh, Miriam, et al.
Publicado: (2024)

Agentar-Fin-OCR
por: Qian, Siyi, et al.
Publicado: (2026)

When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation
por: Sun, Lin, et al.
Publicado: (2026)

OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation
por: Zhang, Junyuan, et al.
Publicado: (2024)

HTR-ConvText: Leveraging Convolution and Textual Information for Handwritten Text Recognition
por: Truc, Pham Thach Thanh, et al.
Publicado: (2025)

Ocean-OCR: Towards General OCR Application via a Vision-Language Model
por: Chen, Song, et al.
Publicado: (2025)

TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Content
por: Anand, Avinash, et al.
Publicado: (2024)

ABot-OCR Technical Report
por: Jiang, Kaitao, et al.
Publicado: (2026)

CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy
por: Yang, Zhibo, et al.
Publicado: (2024)

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
por: Wei, Haoran, et al.
Publicado: (2024)

Error Patterns in Historical OCR: A Comparative Analysis of TrOCR and a Vision-Language Model
por: Vesalainen, Ari, et al.
Publicado: (2026)

Multi-encoder nnU-Net outperforms transformer models with self-supervised pretraining
por: Otaghsara, Seyedeh Sahar Taheri, et al.
Publicado: (2025)

DODO: Discrete OCR Diffusion Models
por: Man, Sean, et al.
Publicado: (2026)

An Empirical Study of Scaling Law for OCR
por: Rang, Miao, et al.
Publicado: (2023)

LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR
por: Taghadouini, Said, et al.
Publicado: (2026)

Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?
por: He, Haibin, et al.
Publicado: (2025)

olmOCR 2: Unit Test Rewards for Document OCR
por: Poznanski, Jake, et al.
Publicado: (2025)

OCR-Quality: A Human-Annotated Dataset for OCR Quality Assessment
por: Zhang, Yulong
Publicado: (2025)

GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer
por: Hasan, Md. Mahmudul, et al.
Publicado: (2025)

DeepSeek-OCR: Contexts Optical Compression
por: Wei, Haoran, et al.
Publicado: (2025)

Exploring OCR-augmented Generation for Bilingual VQA
por: Lee, JoonHo, et al.
Publicado: (2025)

Multimodal OCR: Parse Anything from Documents
por: Zheng, Handong, et al.
Publicado: (2026)

PaddleOCR 3.0 Technical Report
por: Cui, Cheng, et al.
Publicado: (2025)

DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model
por: Chen, Qian, et al.
Publicado: (2025)