Repositori institusi berbasis AI dengan metode retrieval-augmented generation
Abstract
The purpose of this study is to help library users search for information more quickly, accurately, and contextually, and to provide a comprehensive understanding of the concepts and architecture of institutional repositories that use the Retrieval-Augmented Generation (RAG) method. This research adopts a Design Science Research (DSR) approach to address challenges in information retrieval arising from advances in artificial intelligence. The artifact developed is an artificial intelligence-based institutional repository system using the Retrieval-Augmented Generation (RAG) method. The research results regarding the implementation of building an institutional repository with the Retrieval-Augmented Generation (RAG) approach include the stages of identifying conventional repository issues from the past to the present, designing or conceptualizing an RAG-based system, the workflow of implementing RAG technology in institutional repositories, analysis of advantages, and implications for the academic environment. This study concludes that applying RAG to institutional repositories not only increases the efficiency of information search but also enriches the user experience in finding relevant, contextual knowledge. This research offers concrete and applicable solutions to improve the quality of library services in the digital era
References
Chang, S.-H. (2003). Institutional Repositories: the Library’s New Role.Oclc Systems & Services. https://doi.org/10.1108/10650750310733199
Fan, Y., Xia, X., Lo, D., Hassan, A., & Li, S. (2020). What Makes a Popular Academic AI Repository. arXiv: Software Engineering. https://doi.org/10.1007/S10664-020-09916-6
Ginsburg, J. (2010, November 1). A computational model of language generation applied to English wh-questions.Intelligent Systems Design and Applications. https://doi.org/10.1109/ISDA.2010.5687044
Hierry, R., Philippe, N., Vignaux, J.-J., & Barbin, F. (2020).Retriever system for a marine equipment and method.
Lewis, P. S. H., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020, May 22). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.Neural Information Processing Systems.
Liang, D., Ranjith, N., Robin, A., & Vijay, M. (2020).Search engine functionality using shared ai models.
Mao, Y., He, P., Liu, X., Shen, Y., Gao, J., Han, J., & Chen, W. (2021, August 1). Generation-Augmented Retrieval for Open-Domain Question Answering.Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/V1/2021.ACL-LONG.316
Olawade, D. B., Wada, O. Z., Odetayo, A., David-Olawade, A. C., Asaolu, F., & Eberhardt, J. (2024). Enhancing mental health with Artificial Intelligence: Current trends and future prospects.Journal of Medicine, Surgery, and Public Health. https://doi.org/10.1016/j.glmedi.2024.100099
Ruiz-Conde, E., & Calderón-Martínez, A. (2014). University institutional repositories: competitive environment and their role as communication media of scientific knowledge.Scientometrics. https://doi.org/10.1007/S11192-013-1159-5
Zhang, S. (2018, June 26). Information overload and online collaborative learning: insights from agent-based modeling.Learning at Scale. https://doi.org/10.1145/3231644.3231701
