Development of Uzbek Question-Answering Models through Fine-Tuning Approaches
Ilyos KhujayarovDepartment of Information Technology, Tashkent University of Information Technologies named after Muhammad Al-Khwarizmi, Tashkent, UzbekistanMannon OchilovDepartment of Robotics and Intelligent Systems, Tashkent University of Information Technologies named after Muhammad Al-Khwarizmi, Tashkent, UzbekistanMalika AbdullayevaDepartment of Robotics and Intelligent Systems, Tashkent University of Information Technologies named after Muhammad Al-Khwarizmi, Tashkent, UzbekistanOrzimurod KholmatovDepartment of Artificial Intelligence, Tashkent University of Information Technologies named after Muhammad Al-Khwarizmi, Tashkent, UzbekistanRashid NasimovDepartment of Artificial Intelligence, Tashkent State University of Economics, Tashkent, Uzbekistan
2025
ABI
Abstract
In this article, experiments were conducted on modern models such as T5, Flan-T5, mT5 and Llama for use in Retrieval-Augmented Generation (RAG) technologies. During the research, each model was fine-tuned based on a special domain data set consisting of Context, question, and answer columns, and the results were evaluated using evaluation metrics such as BLEU, ROUGE and METEOR. The use of RAG technology allows for searching for the necessary information from external knowledge bases and generating answers to questions. The results obtained are of great importance in the development of question-answer systems in the Uzbek language, including the development of auxiliary systems in areas such as call centers and public services.
Topics
Identifiers
Citations and references
Cited by 028 references
Metrics — AkademScholar · Coming soon