Location
Hilton Waikoloa Village, Hawaii
Event Website
https://hicss.hawaii.edu/
Start Date
7-1-2025 12:00 AM
End Date
10-1-2025 12:00 AM
Description
With the advent of large language models (LLMs), setting chatbot personalities via LLMs has become an important topic to facilitate human-chatbot interaction. To provide clear guidelines and best practices, we conducted a systematic literature review to consolidate various methods, including prompting, fine-tuning, unsupervised machine learning, and knowledge editing. Our research synthesizes findings from numerous studies, providing a comprehensive overview of existing methods and their impact on developing chatbot personalities via LLM approaches. By exploring these methods in detail, we aim to highlight the importance of integrating personality traits into chatbot development. Our goal is to provide developers with the necessary insights to adopt appropriate methods for designing robot personality traits and implementing chatbot applications. Ultimately, our synthesis will enhance the effectiveness and user experience when interacting with LLM personality-based chatbots and suggest future directions to advance the field of LLM personality development.
Recommended Citation
Chang, Ting-Chi; Chen, Yu-Jou; Hung, Sheng; Chang, Ning-Hsuan; Ku, Chih-Hao; Lin, Szu-Yin; and Chien, Shih-Yi, "A Review on Shaping Chatbot Personalities via Large Language Models" (2025). Hawaii International Conference on System Sciences 2025 (HICSS-58). 3.
https://aisel.aisnet.org/hicss-58/da/social_robots/3
A Review on Shaping Chatbot Personalities via Large Language Models
Hilton Waikoloa Village, Hawaii
With the advent of large language models (LLMs), setting chatbot personalities via LLMs has become an important topic to facilitate human-chatbot interaction. To provide clear guidelines and best practices, we conducted a systematic literature review to consolidate various methods, including prompting, fine-tuning, unsupervised machine learning, and knowledge editing. Our research synthesizes findings from numerous studies, providing a comprehensive overview of existing methods and their impact on developing chatbot personalities via LLM approaches. By exploring these methods in detail, we aim to highlight the importance of integrating personality traits into chatbot development. Our goal is to provide developers with the necessary insights to adopt appropriate methods for designing robot personality traits and implementing chatbot applications. Ultimately, our synthesis will enhance the effectiveness and user experience when interacting with LLM personality-based chatbots and suggest future directions to advance the field of LLM personality development.
https://aisel.aisnet.org/hicss-58/da/social_robots/3