کنفرانس بین المللی فناوری اطلاعات و دانش

صفحه اصلی / پانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش

PersianRAG A Retrieval Augmented Generation System for Persian Language

نویسندگان :

Hossein Hosseini¹ Mohammad Sobhan Zare² Amir Hossein Mohammadi³ Arefeh Kazemi⁴ Zahra Zojaji⁵ Mohammad Ali Nematbakhsh⁶

1- دانشگاه اصفهان 2- دانشگاه اصفهان 3- دانشگاه اصفهان 4- دانشگاه اصفهان 5- دانشگاه اصفهان 6- دانشگاه اصفهان

کلمات کلیدی :

Retrieval Augmented Generation،Large Language Models،Persian،PersianRAG

چکیده :

Retrieval augmented generation (RAG) models, which integrate large-scale pre-trained generative models with external retrieval mechanisms, have shown significant success in various natural language processing (NLP) tasks. However, applying RAG models in Persian language as a low-resource language, poses distinct challenges. These challenges primarily involve the preprocessing, embedding, retrieval, prompt construction, language modeling, and response evaluation of the system. In this paper, we address the challenges towards implementing a real-world RAG system for Persian language called PersianRAG. We propose novel solutions to overcome these obstacles and evaluate our approach using several Persian benchmark datasets. Our experimental results demonstrate the capability of the PersianRAG framework to enhance question answering task in Persian.