📄 Paper | 📚 ArXiv | 💻 Code | 🤗 Model Collection ARI-8B is a specialized language model for restoring damaged or illegible Hanja characters in Korean historical records, including the Annals of the Joseon Dynasty (AJD) and the Journal of the Royal Secretariat (JRS). It was developed as a computationally efficient alternative to ARI-32B under the same overall training and optimization framework, while retaining strong restoration performance. It is part of ARI (Archive Restoration Intelligence), a retrieval-augmented historical document restoration framework that combines: — implicit historical and linguistic knowledge encoded in a pretrained LLM, — explicitly retrieved historical documents, — chronological metadata, and — domain-specific supervised fine-tuning. This design is especially effective for restoring named entities, such as personal names, locations, organizations, official titles, dates, and book titles, which often cannot be inferred from local context alone. ARI-8B is the computationally efficient ARI variant, designed to retain strong restoration performance with substantially lower inference cost than ARI-32B. > The released model…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: DAMI-Lab
Теги: qwen3, 8B, restoration, joseon-dynasty, conversational, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 219
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
