Prospects of Retrieval-Augmented Generation (RAG) for Academic Library Search and Retrieval.
This paper examines the integration of retrieval-augmented generation (RAG) systems within academic library environments, focusing on their potential to transform traditional search and retrieval mechanisms. RAG combines the natural language understanding capabilities of large language models with s...
| Publicado en: | Information Technology & Libraries Vol. 44; no. 2; pp. 1 - 16 |
|---|---|
| Autores principales: | , , , , , , |
| Formato: | questions and answers tables/charts Journal Article |
| Publicado: |
American Library Association
Jun2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=186511083&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 186511083 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 07309295 ITL jtl: Information Technology & Libraries issn: 07309295 maglogo: N pubinfo: dt: Jun2025 vid: 44 iid: 2 pid: 55 pub: American Library Association place: Chicago, Illinois artinfo: ui: 186511083 186511083 186511083 10.5860/ital.v44i2.17361 186511083 ppf: 1 ppct: 15 formats: fmt: @attributes: type: P tig: atl: Prospects of Retrieval-Augmented Generation (RAG) for Academic Library Search and Retrieval. aug: au: Kumar Bevara, Ravi Varma Lund, Brady D. Mannuru, Nishith Reddy Karedla, Sai Pranathi Mohammed, Yara Kolapudi, Sai Tulasi Mannuru, Aashrith affil: Doctoral Candidate, University of North Texas sug: subj: Libraries, Academic Computerized Literature Searching Information Retrieval Artificial Intelligence, Generative Libraries, Electronic Information Technology Library Services Collaboration Natural Language Processing Feedback ab: This paper examines the integration of retrieval-augmented generation (RAG) systems within academic library environments, focusing on their potential to transform traditional search and retrieval mechanisms. RAG combines the natural language understanding capabilities of large language models with structured retrieval from verified knowledge bases, offering a novel approach to academic information discovery. The study analyzes the technical requirements for implementing RAG in library systems, including embedding pipelines, vector databases, and middleware architecture for integration with existing library infrastructure. We explore how RAG systems can enhance search precision through semantic indexing, real-time query processing, and contextual understanding while maintaining compliance with data privacy and copyright regulations. The research highlights RAG's ability to improve user experience through personalized research assistance, conversational interfaces, and multimodal content integration. Critical considerations including ethical implications, copyright compliance, and system transparency are addressed. Our findings indicate that while RAG presents significant opportunities for advancing academic library services, successful implementation requires careful attention to technical architecture, data protection, and user trust. The study concludes that RAG integration holds promise for revolutionizing academic library services while emphasizing the need for continued research in areas of scalability, ethical compliance, and cost-effective implementation. pubtype: Academic Journal doctype: questions and answers tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|