PersianRAG: A Retrieval-Augmented Generation System for Persian Language
It addresses challenges in NLP for Persian speakers, but it is incremental as it adapts existing RAG methods to a new language.
The paper tackled the problem of applying retrieval-augmented generation (RAG) models to Persian as a low-resource language, and the result was the PersianRAG system, which enhanced question answering on Persian benchmark datasets.
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.