Masood, Talha (2023) An Overview of the use of Small Scale AI and LLM Models in the context of Receptionist Chatbots. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (10MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
LLM (large language models) are becoming quite widespread in use. They have many use cases, especially in the form of specialized chatbots. One such use case is the use of such models as a receptionist chatbot in an office environment. There is a need to look at various aspects of the outputs of such LLM in order to see how their responses are even suited for use in such models or not. A variety of tools can be used to gauge how well the models perform this work. Using word clouds, sentiment analysis is a baseline way of looking at whether the responses are provided in a professional way or not. In addition, hand collected LLM conversations can be separated into several groups depending on whether or not the request of the prompting user was adequately responded to. The user in this case would ask the chatbot the location of a virtual office environment and the chatbot would be expected to answer with some degree of accuracy. Overall results have been impressive and showcase the performance of existing models.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Basilio, Jorge UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence |
Divisions: | School of Computing > Master of Science in Data Analytics |
Depositing User: | Ciara O'Brien |
Date Deposited: | 18 May 2025 13:23 |
Last Modified: | 18 May 2025 13:23 |
URI: | https://norma.ncirl.ie/id/eprint/7568 |
Actions (login required)
![]() |
View Item |