Author ORCID Identifier
Tsai - https://orcid.org/0000-0001-9188-0362
Chandrasekar - https://orcid.org/0009-0008-8534-8474
Document Type
Poster
Publication Date
6-11-2024
Publication Title
dg.o '24: Proceedings of the 25th Annual International Conference on Digital Government Research
First Page
1020
Last Page
1022
DOI
https://doi.org/10.1145/3657054.3657272
Abstract
The advent of the internet has significantly enhanced accessibility to information, facilitating the engagement of diverse communities with online resources. Despite the abundance of information available, navigating the structures of large organizations and effectively digesting essential personalized information remains a challenge. Consequently, individuals may be deterred from extracting valuable insights from already available resources. This paper addresses this issue by integrating a university’s official website into an AI chatbot powered by large language models (LLMs). We demonstrate use cases to provide information tailored to general information-seeking and personalized information needs for college major selection. We present a novel approach for individuals to gain insights into large organizations via interactive conversation. Based on our system demonstration, we further delve into the role of generative AI in synthesizing vast organizational datasets into user-friendly formats accessible to the public and its implications for E-government and open government research.
Recommended Citation
Haresh Chandrasekar, Srishti Gupta, Chun-Tzu Liu, and Chun-Hua Tsai. 2024. Leveraging Large Language Models for Effective Organizational Navigation. In Proceedings of the 25th Annual International Conference on Digital Government Research (dg.o '24). Association for Computing Machinery, New York, NY, USA, 1020–1022. https://doi.org/10.1145/3657054.3657272
Comments
© {Authors | ACM} {Year}. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in { Proceedings of the 25th Annual International Conference on Digital Government Research
}, https://doi.org/10.1145/3657054.3657272