Proceedings of the 2023 3rd International Conference on Education, Information Management and Service Science (EIMSS 2023)

<Previous Article In Volume
Next Article In Volume>

Sematic Search Augmented Conversation for Enhanced Dialogue Generation

Authors
Yibo Yao1, Azlan Mohd Zain1, *, Kai-Qing Zhou2
1Faculty of Computing, Universiti Teknologi Malaysia, 80310, Skudai, Johor, Malaysia
2School of Communication and Electronic Engineering, Jishou University, Jishou, China
*Corresponding author. Email: azlanmz@utm.my
Corresponding Author
Azlan Mohd Zain
Available Online 28 September 2023.
DOI
10.2991/978-94-6463-264-4_84How to use a DOI?
Keywords
LLMs; semantic search; knowledge; prompt tuning; conversation generation
Abstract

Although advanced conversational models like ChatGPT are capable of generating rich and coherent content, the generated responses often contain fictional facts and knowledge hallucinations. A mainstream approach to addressing this problem in the past has been fine-tuning or retraining models by injecting external knowledge into pre-trained language models. However, given the enormous scale of current state-of-the-art language models, these methods require continuous retraining to update the knowledge embedded in the model parameters, which is undeniably challenging, slow, expensive, and the updated models lack scalability. In this work, we explore the use of semantic search based on user input and local knowledge to prompt language models for enhanced dialogue generation. We experiment with different domains of dialogue on four popular large language models (LLMs), and the results show that our approach, compared to the method of injecting knowledge into LLMs, can effectively improve the utilization efficiency of knowledge, significantly reduce knowledge hallucination problems, and has almost unlimited scalability.

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 2023 3rd International Conference on Education, Information Management and Service Science (EIMSS 2023)
Series
Atlantis Highlights in Computer Sciences
Publication Date
28 September 2023
ISBN
10.2991/978-94-6463-264-4_84
ISSN
2589-4900
DOI
10.2991/978-94-6463-264-4_84How 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  - Yibo Yao
AU  - Azlan Mohd Zain
AU  - Kai-Qing Zhou
PY  - 2023
DA  - 2023/09/28
TI  - Sematic Search Augmented Conversation for Enhanced Dialogue Generation
BT  - Proceedings of the 2023 3rd International Conference on Education, Information Management and Service Science (EIMSS 2023)
PB  - Atlantis Press
SP  - 734
EP  - 740
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-264-4_84
DO  - 10.2991/978-94-6463-264-4_84
ID  - Yao2023
ER  -