A Large Language Model-Based Question An swering System for Online Public Administra tive Services

  • Dinh - Dien La Department of Information and Communications, Ha Giang Province, Viet Nam
  • Tuan - Anh Nguyen Institute of Applied Science and Technology- IAST, University of Information and Communication Technology, Thai Nguyen University, Vietnam
  • Duc - Huy Mai Institute of Applied Science and Technology- IAST, University of Information and Communication Technology, Thai Nguyen University, Vietnam
  • Thi - Thanh Ha Institute of Applied Science and Technology- IAST, University of Information and Communication Technology, Thai Nguyen University, Vietnam
  • Trung - Nghia Phung Institute of Applied Science and Technology- IAST, University of Information and Communication Technology, Thai Nguyen University, Vietnam
  • Van-Khanh Tran Viện IAST - ICTU
DOI: https://doi.org/10.32913/mic-ict-research-vn.v2024.n3.1290
Keywords: Question answering system, public administrative services, large language model

Abstract

Public administrative services are one of the key concerns for citizens; however, there are still numerous
procedures and issues that citizens encounter and need clarification on. This study aims to alleviate some of this burden on officials by developing a Question Answering System (QnA) to address inquiries about public administrative services. We present a framework for utilizing Large Language Models to develop and implement a QnA system on the Online Public Administrative Service Portal in Ha Giang Province. We also provide extensive experimental analysis to demonstrate the effectiveness of each component in the QnA system.

Author Biographies

Dinh - Dien La, Department of Information and Communications, Ha Giang Province, Viet Nam

Dinh-Dien La is a PhD student majoring in computer science, University of Information and Communications Technology, Thai Nguyen University. He is currently Deputy Director of the Department of Information and Communications of Ha Giang province. His research interests are data science, machine learning, and deep
learning.

Tuan - Anh Nguyen, Institute of Applied Science and Technology- IAST, University of Information and Communication Technology, Thai Nguyen University, Vietnam

Tuan-Anh Nguyen is pursuing an Engineering degree in Information Technology at the University of  Information and Communication Technology in Thai Nguyen, Vietnam. He is involved with the Institute
of Applied Science and Technology in Thai Nguyen. His research interests include machine learning, deep learning, and natural language processing.

Duc - Huy Mai, Institute of Applied Science and Technology- IAST, University of Information and Communication Technology, Thai Nguyen University, Vietnam

Duc-Huy Mai is pursuing the B.Eng degree in Information Technology from Thai Nguyen University of Information and Communication Technology (ICTU). His research interests include software development, natural language processing (NLP), and question answering.

Thi - Thanh Ha, Institute of Applied Science and Technology- IAST, University of Information and Communication Technology, Thai Nguyen University, Vietnam

Thi-Thanh Ha received PhD degree in Information System in Ha Noi University of Science and Technology, Viet Nam. She obtained Bachelor Degree of Science in Applied Mathematics and Informatics from University of Natural Science, Vietnam National University in 2004. She currently is a lecturer at Computer Science in Thai Nguyen University of Information and Communication Technology. Her research interests are fields of deep learning in Natural Language Processing, Question Answering, and chatbot.

Trung - Nghia Phung, Institute of Applied Science and Technology- IAST, University of Information and Communication Technology, Thai Nguyen University, Vietnam

Assoc. Prof. Trung-Nghia Phung received his Engineering degree in Electronics and Telecommunications from Hanoi University of Science and Technology (HUST) in 2002. He completed his Master of Science degree in Telecommunications from Vietnam National University–Hanoi (VNUH) in 2007 and his PhD degree in Information Science from Japan Advanced Institute of Science and Technology (JAIST) in 2013. He has been Rector of Thai Nguyen University of Information and Communication Technology (ICTU). His main research interests are signal processing and machine learning.

Van-Khanh Tran, Viện IAST - ICTU

Van-Khanh Tran received Ph.D. in Natural Language Processing from the Japan Advanced Institute of Science and Technology (JAIST), where his research focused on deep learning for natural language generation in spoken dialogue systems. contributed to the development of NLP applications. He is currently an AI Research
Scientist on the NLP team at FPT Smart Cloud’s Generative AI (GenAI) Center, where he focuses on developing large language models and AI assistant ecosystems tailored for Vietnamese users. He also serves as the Deputy Head of the Institute of Applied Science and Technology. His research interests include natural
language processing, large language models, and AI applications in the legal, healthcare, and finance domains.

References

J. Martinez-Gil, “A survey on legal question–answering systems,” Computer Science Review, vol. 48, p. 100552,

G. Caldarini, S. F. Jaf, and K. McGarry, “A literature survey of recent advances in chatbots,” CoRR, vol. abs/2201.06657, 2022. [Online]. Available: https://arxiv.org/abs/2201.06657

S. Minaee, T. Mikolov, N. Nikzad, M. Chenaghlu, R. Socher, X. Amatriain, and J. Gao, “Large language models: A survey,” 2024.

A. Torfi, R. A. Shirvani, Y. Keneshloo, N. Tavaf, and E. A. Fox, “Natural language processing advancements

by deep learning: A survey,” 2021. [Online]. Available: https://arxiv.org/abs/2003.01200

A. Pham Duy and H. Le Thanh, “A question-answering system for vietnamese public administrative services,” in Proceedings of the 12th SoICT, ser. SOICT ’23, 2023.

E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, and W. Chen, “Lora: Low-rank adaptation of large language models,” CoRR, vol. abs/2106.09685, 2021.

S. Robertson and H. Zaragoza, “The probabilistic relevance framework: Bm25 and beyond,” FTIR, vol. 3, pp. 333–389, 01 2009.

J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers

for language understanding,” 2019. [Online]. Available: https://arxiv.org/abs/1810.04805

N. Reimers and I. Gurevych, “Sentence-bert: Sentence embeddings using siamese bert-networks,” 2019. [Online]. Available: https://arxiv.org/abs/1908.10084

N. Q. Duc, L. H. Son, N. D. Nhan, N. D. N. Minh, L. T. Huong, and D. V. Sang, “Towards comprehensive vietnamese rag and llms,” arXiv preprint arXiv:2403.01616, 2024.

X. Amatriain, “Prompt design and engineering: Introduction and advanced methods,” arXiv preprint arXiv:2401.14423, 2024.

S. Es, J. James, L. Espinosa-Anke, and S. Schockaert, “Ragas: Automated evaluation of retrieval augmented generation,” arXiv preprint arXiv:2309.15217, 2023.

C. Nguyen, S. Luu, T. Tran, A. Trieu, A. Dang, D. Nguyen, H. Nguyen, T. Pham, T. Pham, T.-T. Vo, D.-T. Dol, N. Khang, H. Nguyen, N.-C. Le, T.-T. Le, Q. Bui, P. Nguyen, H.-T. Nguyen, V. Tran, and L. Nguyen, “A summary of the alqac 2023 competition,” 10 2023, pp. 1–6.

M. Eibich, S. Nagpal, and A. Fred-Ojala, “Aragog: Advanced rag output grading,” 2024. [Online]. Available:

https://arxiv.org/abs/2404.01037

L. Wang, C. Ma, X. Feng, Z. Zhang, H. Yang, J. Zhang, Z. Chen, J. Tang, X. Chen, Y. Lin, W. X. Zhao, Z. Wei, and J. Wen, “A survey on llm based autonomous agents,” Frontiers of Computer Science, vol. 18, no. 6, Mar. 2024.

Published
2024-09-13
Issue
Tập 2024 Số 3: Các công trình nghiên cứu, phát triển và ứng dụng Công nghệ Thông tin và Truyền thông
Section
Bài báo

Copyright Agreement