International Conference on Computer and Knowledge Engineering

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 Kashaniyan¹ Amirhossein Ghassemi² Nasser Mozayani³

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

Analysis of Address Lifespans in Bitcoin and Ethereum

Amir Mohammad Karimi Mamaghan - Amin Setayesh - Behnam Bahrak

Improvement of Credit Scoring by LSTM Autoencoder Model

Milad Sattari Maleki - Seyedeh Niusha Motevallian - Faezehsadat Hosseini - Mohammad Sabokrou - Hamidreza Soltanalizadeh Maleki

Swin-RSCBNet: A Transformer-Based Network for Skin Cancer Segmentation with Multi-Scale and Attention Modules

Benyamin Mirab Golkhatmi - Mostafa Heydari - Mahboobeh Houshmand - Seyyed Abed Hosseini

Adversarial Robustness Evaluation with Separation Index

Bahareh Kaviani Baghbaderani - Afsaneh Hasanebrahimi - Ahmad Kalhor - Reshad Hosseini

Paddy Plant Stress Identification Using Few-Shot Learning Framework

Ervin Gubin Moung - Pavindrah Naidu a/l Narayanasamy Naiidu - Maisarah Mohd Sufian - Valentino Liaw - Ali Farzamnia - Lorita Angeline

FedFog: A Serverless and Privacy-Aware Federated Learning Simulator for Edge–Fog Networks

Seyed Vahid Hashemi Nik - Seyed Mohammad Mahdi Asaadi - Somayeh Sobati-M

Developing Convolutional Neural Networks using a Novel Lamarckian Co-Evolutionary Algorithm

Zaniar Sharifi - Khabat Soltanian - Ali Amiri

User Behavior Analysis : A Framework for Web Systems with Adaptive User Interfaces Using Unsupervised Modeling

Ali Bajelan - Ehsan Khadangi (Corresponding Author)

Efficient Object Detection using Deep Reinforcement Learning and Capsule Networks

Sobhan Siamak - Eghbal Mansoori

Classification of COVID-19 and Nodule in CT Images using Deep Convolutional Neural Network

Amirhossein Ghaemi - Seyyed Amir Mousavi mobarakeh - Habibollah Danyali - Kamran Kazemi