Logo des Repositoriums
 

On Data Spaces for Retrieval Augmented Generation

Kurzanzeige
dc.contributor.authorHermsen, Felix
dc.contributor.authorNitz, Lasse
dc.contributor.authorAkbari Gurabi, Mehdi
dc.contributor.authorMatzutt, Roman
dc.contributor.authorMandal, Avikarsha
dc.contributor.editorKlein, Maike
dc.contributor.editorKrupka, Daniel
dc.contributor.editorWinter, Cornelia
dc.contributor.editorGergeleit, Martin
dc.contributor.editorMartin, Ludger
dc.date.accessioned2024-10-21T18:24:28Z
dc.date.available2024-10-21T18:24:28Z
dc.date.issued2024
dc.description.abstractLarge Language Models (LLMs) have revolutionized knowledge retrieval from natural language queries. However, LLMs still face challenges regarding the creation of domain-specific and accurate answers. Recently, Retrieval Augmented Generation (RAG) architecture has been proposed as one approach to addressing these challenges. While current research focuses on optimizing document retrieval and augmenting the initial query accordingly, we identify untapped potentials of RAG to retrieve knowledge from heterogeneous data sources via data spaces. In this work, we investigate three conceptual integration scenarios between RAG and data spaces. Our findings indicate that given the data space extended RAG, it could provide domain-specific information retrieval with diverse data sources. However, solutions to mitigate unintended information leakage require further consideration.en
dc.identifier.doi10.18420/inf2024_57
dc.identifier.isbn978-3-88579-746-3
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/45218
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofINFORMATIK 2024
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-352
dc.subjectData Spaces
dc.subjectLarge Language Models
dc.subjectRetrieval Augmented Generation
dc.subjectData Sharing
dc.titleOn Data Spaces for Retrieval Augmented Generationen
dc.typeText/Conference Paper
gi.citation.endPage707
gi.citation.publisherPlaceBonn
gi.citation.startPage701
gi.conference.date24.-26. September 2024
gi.conference.locationWiesbaden
gi.conference.sessiontitleGRANITE – EJEA: Europe meets Japan: Intercultural Workshop on Data Sovereignty and Generative AI: Applications, Design, Social, Ethical and Technological Impact

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
Hermsen_et_al_On_Data_Spaces.pdf
Größe:
709.13 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P352 - INFORMATIK 2024 - Lock in or log out? Wie digitale Souveränität gelingt