Proceedings of the 2024 3rd International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID 2024)

<Previous Article In Volume
Next Article In Volume>

Research on Self-inspired Intelligent Question Answering Method Based on Socratic Questioning

Authors
Zhichao Yao1, *, Haoran Ji2
193357 Troops, People’s Liberation Army of China, Anshan, 114020, China
2Intelligent Game and Decision Lab, Academy of Military Science, Beijing, 100071, China
*Corresponding author. Email: yaozhichao18@nudt.edu.cn
Corresponding Author
Zhichao Yao
Available Online 31 August 2024.
DOI
10.2991/978-94-6463-490-7_14How to use a DOI?
Keywords
Socratic questioning; large language model; Prompt Engineering; self-inspired
Abstract

Large language model has become one of the hot research contents in the field of artificial intelligence due to its excellent ability in natural language processing tasks. However, large language models usually have the disadvantages of over-reliance on surface statistical information and lack of deep understanding of the problem, which affects the accuracy and credibility of their answers. This paper first introduces the connotation of Socratic questioning, then proposes a self-inspired intelligent question answering method based on Socratic Questioning, and verifies the reliability of this method through example comparison. The results show that this method can guide the self-inspired deep thinking of large language models, stimulate the intelligent emergence of large language models, and make the answer results more accurate and comprehensive.

Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2024 3rd International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID 2024)
Series
Atlantis Highlights in Intelligent Systems
Publication Date
31 August 2024
ISBN
978-94-6463-490-7
ISSN
2589-4919
DOI
10.2991/978-94-6463-490-7_14How to use a DOI?
Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Zhichao Yao
AU  - Haoran Ji
PY  - 2024
DA  - 2024/08/31
TI  - Research on Self-inspired Intelligent Question Answering Method Based on Socratic Questioning
BT  - Proceedings of the 2024 3rd International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID 2024)
PB  - Atlantis Press
SP  - 115
EP  - 127
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-490-7_14
DO  - 10.2991/978-94-6463-490-7_14
ID  - Yao2024
ER  -