Please wait ...
0% Complete
Home
/
15th International Conference on Computer and Knowledge Engineering
LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4
Authors :
Mobina Kashaniyan
1
Amirhossein Ghassemi
2
Nasser Mozayani
3
1- Iran University of Science and Technology
2- Iran University of Science and Technology
3- Iran University of Science and Technology
Keywords :
large language models،neural architecture search،handwritten text recognition،multilingual OCR،automation،model discovery
Abstract :
Handwritten text recognition across diverse scripts presents an enduring challenge in machine learning, as each language and writing system introduces unique visual complexities and demands. Traditional approaches have depended on expertguided model design and extensive preprocessing, which make it difficult to scale and adapt to new scripts efficiently. In this work, we introduce a pipeline that is fully automatic and cross lingual, using large language models, GPT 5, GPT 4o and Claude Sonnate 4, to independently generate, evaluate, and refine neural network architectures for handwritten optical character recognition. This process requires no manual intervention, domain specific preprocessing, or human selection of models, resulting in a complete end to end automated system. We apply this approach to Arabic, English, and Persian scripts, each representing distinct character shapes and writing traditions, and conduct thirty independent trials for every language. The pipeline consistently discovers efficient models with high test accuracy, achieving average scores above ninety three percent, while also maintaining inference speeds that meet the needs of real time applications. Notably, the system is able to automatically explore a wide range of neural architectures and adaptively select designs that fit the unique requirements of each script, without any explicit guidance from human experts. These results show that large language models can move beyond language processing and act as independent designers for machine learning systems. This enables a scalable, script agnostic, and fully automatic solution for multilingual handwritten text recognition, opening the door to rapid and adaptable deployment of OCR technology across many languages and domains.
Papers List
List of archived papers
Enhancing Persian Word Sense Disambiguation with Large Language Models: Techniques and Applications
Fatemeh Zahra Arshia - Saeedeh Sadat Sadidpour
Enhanced Autoencoder-based Clustering for Message Analysis in Binary Protocols
Mohaddese Nemati - Shiva Mahmoudzadeh - Mehdi Teimouri
Impact of Oversampling Methods on Imbalanced Dataset for Software Fault Prediction
Alireza Abiri - Alireza Tajary - Mansoor Fateh
VVC-AAR: Adaptive Attention-Aware Resolution and Residual Coding for Perceptually Optimized Ultra-Low Bitrate VVC Compression
Yaghoub Saberi - Somayeh Arab Najafabadi - Mohammadreza Hemmati
AvashoG2P: A multi-module G2P Converter for Persian
Ali Moghadaszadeh - Fatemeh Pasban - Mohsen Mahmoudzadeh - Maryam Vatanparast - Amirmohammad Salehoof
A Synergistic Hybrid Architecture with Residual Attention and Mixture-of-Experts for Robust Hour-Ahead Forex Forecasting
Alireza Abbaszadeh - Seyyed Abed Hosseini - Mohammad Reza Akbarzadeh Totonchi
ExaAEC: A New Multi-label Emotion Classification Corpus in Arabic Tweets
Saeed Sarbazi-Azad - Ahmad Akbari - Mohsen Khazeni
Joint mobility-aware offloading and UAV position optimization in Blockchain-enabled 5G
Zeinab Rabbani - Zeinab Movahedi
PowerLinear Activation Functions with application to the first layer of CNNs
Kamyar Nasiri - Kamaledin Ghiasi-Shirazi
Efficient Object Detection using Deep Reinforcement Learning and Capsule Networks
Sobhan Siamak - Eghbal Mansoori
more
Samin Hamayesh - Version 46.0.2