Date of this Version
12-2024
Document Type
Conference Proceeding
Abstract
This presentation explores the comparative performance of traditional information retrieval systems, such as Solr, against emerging Generative AI (GenAI) models like GPT-4 for digital library resource discovery. Using Miami Life newspaper issues (1920s–1940s) as a case study, the team evaluated both approaches based on relevance, efficiency, user engagement, and system complexity. Findings indicate that while Solr offers faster, scalable keyword-based results, LLM-based systems provide superior contextual understanding and conversational interaction. The study recommends a hybrid framework combining Solr and GenAI models to optimize both precision and user experience in digital libraries.
Recommended Citation
Guan, Boyuan; Rogers, Jamie; Cui, Wencong; and Bakker, Rebecca, "Generative AI for Enhanced Resource Discovery: Comparative Analysis with Solr in Digital Libraries" (2024). Works of the FIU Libraries. 173.
https://digitalcommons.fiu.edu/glworks/173
Full Paper
Rights Statement
In Copyright - Educational Use Permitted. URI: http://rightsstatements.org/vocab/InC-EDU/1.0/
This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. In addition, no permission is required from the rights-holder(s) for educational uses. For other uses, you need to obtain permission from the rights-holder(s).
Comments
This presentation was developed for the ACM/IEEE JCDL 2024 workshop Digital Libraries in the Age of AI: Challenges and Opportunities, held in Hong Kong.