Publication: Retrieval Augmented Generation Based Thai Question-Answering System
8
0
Issued Date
2024-01-01
Resource Type
Scopus ID
2-s2.0-86000032766
Journal Title
ICBIR 2024 - 2024 9th International Conference on Business and Industrial Research, Proceedings
Start Page
794
End Page
798
Rights Holder(s)
SCOPUS
Bibliographic Citation
ICBIR 2024 - 2024 9th International Conference on Business and Industrial Research, Proceedings (2024) , 794-798
Suggested Citation
Yookasame P., Pramoun T., Thewsuwan S. Retrieval Augmented Generation Based Thai Question-Answering System. ICBIR 2024 - 2024 9th International Conference on Business and Industrial Research, Proceedings (2024) , 794-798. 798. doi:10.1109/ICBIR61386.2024.10875697 Retrieved from: https://hdl.handle.net/20.500.14740/20111
Author(s)
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
This paper proposes a Thai Question-Answering System, specifically developed by using the Computer Engi-neering curriculum at Srinakharinwirot University, Thailand. The proposed system integrates the OpenThaiGPT model within a Retrieval-Augmented Generation (RAG) framework to generate contextually accurate responses to user queries. To evaluate the system, a set of 41 questions are categorized into basic, intermediate, and advanced levels, employing both zero-shot and few-shot learning techniques to assess its performance. The experimental results show that few-shot prompting exhibits efficacy across most criteria and complex-ity levels. However, challenges in maintaining this efficacy were observed, particularly regarding the accuracy of responses. This highlights areas that require future improvement.