{"id":"https://openalex.org/W6906711825","doi":"https://doi.org/10.18420/inf2024_57","title":"On Data Spaces for Retrieval Augmented Generation","display_name":"On Data Spaces for Retrieval Augmented Generation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6906711825","doi":"https://doi.org/10.18420/inf2024_57"},"language":"en","primary_location":{"id":"pmh:oai:publica.fraunhofer.de:publica/484283","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/484283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/inf2024_57","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hermsen, Felix","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hermsen, Felix","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Nitz, Lasse","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nitz, Lasse","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Akbari Gurabi, Mehdi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akbari Gurabi, Mehdi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Matzutt, Roman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matzutt, Roman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mandal, Avikarsha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mandal, Avikarsha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31872215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6215000152587891,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6215000152587891,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.1446000039577484,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.0421999990940094,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-retrieval","display_name":"Data retrieval","score":0.5134000182151794},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4104999899864197},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.4099000096321106},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.40939998626708984},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4025999903678894},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.3808000087738037},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.37860000133514404},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.35920000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791100025177002},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6126000285148621},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.40939998626708984},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C162763945","wikidata":"https://www.wikidata.org/wiki/Q4825467","display_name":"Conceptual architecture","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C21025794","wikidata":"https://www.wikidata.org/wiki/Q5141219","display_name":"Cognitive models of information retrieval","level":4,"score":0.3089999854564667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2780613888","wikidata":"https://www.wikidata.org/wiki/Q6423394","display_name":"Knowledge retrieval","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:publica.fraunhofer.de:publica/484283","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/484283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},{"id":"doi:10.18420/inf2024_57","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_57","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18420/inf2024_57","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_57","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7560407519340515,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"revolutionized":[5],"knowledge":[6,63],"retrieval":[7,48,100],"from":[8,64],"natural":[9],"language":[10],"queries.":[11],"However,":[12,105],"LLMs":[13],"still":[14],"face":[15],"challenges":[16],"regarding":[17],"the":[18,51,90],"creation":[19],"of":[20,59],"domain-specific":[21,98],"and":[22,49,82],"accurate":[23],"answers.":[24],"Recently,":[25],"Retrieval":[26],"Augmented":[27],"Generation":[28],"(RAG)":[29],"architecture":[30],"has":[31],"been":[32],"proposed":[33],"as":[34],"one":[35],"approach":[36],"to":[37,61,107],"addressing":[38],"these":[39],"challenges.":[40],"While":[41],"current":[42],"research":[43],"focuses":[44],"on":[45],"optimizing":[46],"document":[47],"augmenting":[50],"initial":[52],"query":[53],"accordingly,":[54],"we":[55,74],"identify":[56],"untapped":[57],"potentials":[58],"RAG":[60,81],"retrieve":[62],"heterogeneous":[65],"data":[66,69,83,91,103],"sources":[67],"via":[68],"spaces.":[70,84],"In":[71],"this":[72],"work,":[73],"investigate":[75],"three":[76],"conceptual":[77],"integration":[78],"scenarios":[79],"between":[80],"Our":[85],"findings":[86],"indicate":[87],"that":[88],"given":[89],"space":[92],"extended":[93],"RAG,":[94],"it":[95],"could":[96],"provide":[97],"information":[99,110],"with":[101],"diverse":[102],"sources.":[104],"solutions":[106],"mitigate":[108],"unintended":[109],"leakage":[111],"require":[112],"further":[113],"consideration.":[114]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}