Abstract
This study investigates the potential of a Large Language Model (LLM) as a Chatbot Development Platform (CDP) for designing dialog systems in the context of conversational agents. While traditional systems often combine rule-based and machine learning approaches via third-party platforms for dialog design, this research explored the utilization of GPT for this purpose, especially for intent and entity detection integral to CDPs. Through a fine-tuning process, two GPT models were adapted to enhance their performance in these tasks, resulting in time and resource efficiency. The resultant system offers a flexible and adaptable framework for chatbot design, with fine-tuning showing significant benefits in maintaining output consistency and saving GPT tokens. The intent classifier demonstrated high precision (99.056%). However, the system faced challenges with dynamic entities, such as dates, due to GPT’s inability to access real-time data. Despite this, the study highlighted the immense potential of GPT and similar LLMs in developing conversational agents while drawing attention to the challenges of handling dynamic entities. These findings signal opportunities for innovative fine-tuning and system integration strategies, encouraging continued research in the dynamic field of conversational AI.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Abdullah, M., Madain, A., Jararweh, Y.: Chatgpt: fundamentals, applications and social impacts. In: 2022 Ninth International Conference on Social Networks Analysis, Management and Security (SNAMS), pp. 1–8 (2022). 10.1109/SNAMS58071.2022.10062688
Daniel, G., Cabot, J., Deruelle, L., Derras, M.: Xatkit: a multimodal low-code chatbot development framework. IEEE Access 8, 15332–15346 (2020). https://doi.org/10.1109/ACCESS.2020.2966919
Husak, V., Lozynska, O., Karpov, I., Peleshchak, I., Chyrun, S., Vysotskyi, A.: Information system for recommendation list formation of clothes style image selection according to user’s needs based on nlp and chatbots. 2604, 788–818 (2020)
MacEclo, P., Pereira, C., Mota, P., Silva, D., Frade, A., Madeira, R.N.: Conversational agent in mhealth to empower people managing Parkinson’s disease. 160, 402–408 (2019). https://doi.org/10.1016/j.procs.2019.11.074
Motger, Q., Franch, X., Marco, J.: Software-based dialogue systems: survey, taxonomy, and challenges. ACM Comput. Surv. 55(5) (2022). https://doi.org/10.1145/3527450
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)
Ralston, K., Chen, Y., Isah, H., Zulkernine, F.: A voice interactive multilingual student support system using ibmwatson, pp. 1924 –1929 (2019). https://doi.org/10.1109/ICMLA.2019.00309
Ray, P.: Chatgpt: a comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet of Things and Cyber-Physical Systems 3 (2023). https://doi.org/10.1016/j.iotcps.2023.04.003
Safi, Z., Abd-Alrazaq, A., Khalifa, M., Househ, M.: Technical aspects of developing chatbots for medical applications: scoping review. J. Med. Internet Res. 22(12), e19127 (2020)
Samuel, I., Ogunkeye, F.A., Olajube, A., Awelewa, A.: Development of a voice chatbot for payment using amazon LEX service with eyowo as the payment platform, pp. 104–108 (2020). https://doi.org/10.1109/DASA51403.2020.9317214
Villa, L., Hervás, R., Cruz-Sandoval, D., Favela, J.: Design and evaluation of proactive behavior in conversational assistants: approach with the eva companion robot. In: Bravo, J., Ochoa, S., Favela, J. (eds.) Proceedings of the International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2022), pp. 234–245. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-21333-5_23
Villa, L., Hervás, R., Dobrescu, C.C., Cruz-Sandoval, D., Favela, J.: Incorporating affective proactive behavior to a social companion robot for community dwelling older adults. In: Stephanidis, C., Antona, M., Ntoa, S., Salvendy, G. (eds.) HCI International 2022 - Late Breaking Posters, pp. 568–575. Springer Nature Switzerland, Cham (2022). https://doi.org/10.1007/978-3-031-19682-9_72
Zhao, W.X., et al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)
Acknowledgements
This work was supported by SHARA3 project, funded by Junta de Comunidades de Castilla - La Mancha (SBPLY/21/180501/000160); TAICare project, as part of the Proyectos Estratégicos Orientados a la Transición Ecológica y a la Transición Digital 2021, financed by Agencia Estatal de Investigación (TED2021-130296A-I00); SSITH project, under Proyectos Prueba de Concepto, funded by Ministerio de Ciencia e Innovación (PDC2022-133457-I00); and the 2022-PRED-20651 predoctoral contract by the UNIVERSITY OF CASTILLA-LA MANCHA.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Villa, L., Carneros-Prado, D., Sánchez-Miguel, A., Dobrescu, C.C., Hervás, R. (2023). Conversational Agent Development Through Large Language Models: Approach with GPT. In: Bravo, J., Urzáiz, G. (eds) Proceedings of the 15th International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2023). UCAmI 2023. Lecture Notes in Networks and Systems, vol 835. Springer, Cham. https://doi.org/10.1007/978-3-031-48306-6_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-48306-6_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48305-9
Online ISBN: 978-3-031-48306-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)