{"id":"https://openalex.org/W4407298138","doi":"https://doi.org/10.3390/make7010015","title":"Investigating the Performance of Retrieval-Augmented Generation and Domain-Specific Fine-Tuning for the Development of AI-Driven Knowledge-Based Systems","display_name":"Investigating the Performance of Retrieval-Augmented Generation and Domain-Specific Fine-Tuning for the Development of AI-Driven Knowledge-Based Systems","publication_year":2025,"publication_date":"2025-02-10","ids":{"openalex":"https://openalex.org/W4407298138","doi":"https://doi.org/10.3390/make7010015"},"language":"en","primary_location":{"id":"doi:10.3390/make7010015","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7010015","pdf_url":"https://www.mdpi.com/2504-4990/7/1/15/pdf?version=1739184685","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/7/1/15/pdf?version=1739184685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032731779","display_name":"R\u00f3bert Lakatos","orcid":"https://orcid.org/0009-0003-9349-3077"},"institutions":[{"id":"https://openalex.org/I132735039","display_name":"University of Debrecen","ror":"https://ror.org/02xf66n48","country_code":"HU","type":"education","lineage":["https://openalex.org/I132735039"]},{"id":"https://openalex.org/I4210142209","display_name":"John von Neumann University","ror":"https://ror.org/03n9qzd79","country_code":"HU","type":"education","lineage":["https://openalex.org/I4210142209"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"R\u00f3bert Lakatos","raw_affiliation_strings":["Department of Data Science and Visualization, Faculty of Informatics, University of Debrecen, 4032 Debrecen, Hungary","Doctoral School of Informatics, University of Debrecen, 4032 Debrecen, Hungary","Neumann Technology Platform, Neumann Nonprofit Ltd., 1074 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0009-0003-9349-3077","affiliations":[{"raw_affiliation_string":"Department of Data Science and Visualization, Faculty of Informatics, University of Debrecen, 4032 Debrecen, Hungary","institution_ids":["https://openalex.org/I132735039"]},{"raw_affiliation_string":"Doctoral School of Informatics, University of Debrecen, 4032 Debrecen, Hungary","institution_ids":["https://openalex.org/I132735039"]},{"raw_affiliation_string":"Neumann Technology Platform, Neumann Nonprofit Ltd., 1074 Budapest, Hungary","institution_ids":["https://openalex.org/I4210142209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012976652","display_name":"P\u00e9ter Pollner","orcid":"https://orcid.org/0000-0003-0464-4893"},"institutions":[{"id":"https://openalex.org/I101202996","display_name":"Semmelweis University","ror":"https://ror.org/01g9ty582","country_code":"HU","type":"education","lineage":["https://openalex.org/I101202996"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"P\u00e9ter Pollner","raw_affiliation_strings":["Data-Driven Health Division of National Laboratory for Health Security, Health Services Management Training Centre, Semmelweis University, 1085 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0003-0464-4893","affiliations":[{"raw_affiliation_string":"Data-Driven Health Division of National Laboratory for Health Security, Health Services Management Training Centre, Semmelweis University, 1085 Budapest, Hungary","institution_ids":["https://openalex.org/I101202996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061104387","display_name":"Andr\u00e1s Hajd\u00fa","orcid":"https://orcid.org/0000-0003-1718-9770"},"institutions":[{"id":"https://openalex.org/I132735039","display_name":"University of Debrecen","ror":"https://ror.org/02xf66n48","country_code":"HU","type":"education","lineage":["https://openalex.org/I132735039"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s Hajdu","raw_affiliation_strings":["Department of Data Science and Visualization, Faculty of Informatics, University of Debrecen, 4032 Debrecen, Hungary"],"raw_orcid":"https://orcid.org/0000-0003-1718-9770","affiliations":[{"raw_affiliation_string":"Department of Data Science and Visualization, Faculty of Informatics, University of Debrecen, 4032 Debrecen, Hungary","institution_ids":["https://openalex.org/I132735039"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006972645","display_name":"Tam\u00e1s Jo\u00f3","orcid":"https://orcid.org/0000-0002-3551-6125"},"institutions":[{"id":"https://openalex.org/I101202996","display_name":"Semmelweis University","ror":"https://ror.org/01g9ty582","country_code":"HU","type":"education","lineage":["https://openalex.org/I101202996"]},{"id":"https://openalex.org/I4210142209","display_name":"John von Neumann University","ror":"https://ror.org/03n9qzd79","country_code":"HU","type":"education","lineage":["https://openalex.org/I4210142209"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Tam\u00e1s Jo\u00f3","raw_affiliation_strings":["Data-Driven Health Division of National Laboratory for Health Security, Health Services Management Training Centre, Semmelweis University, 1085 Budapest, Hungary","Neumann Technology Platform, Neumann Nonprofit Ltd., 1074 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0002-3551-6125","affiliations":[{"raw_affiliation_string":"Data-Driven Health Division of National Laboratory for Health Security, Health Services Management Training Centre, Semmelweis University, 1085 Budapest, Hungary","institution_ids":["https://openalex.org/I101202996"]},{"raw_affiliation_string":"Neumann Technology Platform, Neumann Nonprofit Ltd., 1074 Budapest, Hungary","institution_ids":["https://openalex.org/I4210142209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006972645","https://openalex.org/A5032731779"],"corresponding_institution_ids":["https://openalex.org/I101202996","https://openalex.org/I132735039","https://openalex.org/I4210142209"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":45.5009,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.99797642,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"7","issue":"1","first_page":"15","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9908000230789185,"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":0.9908000230789185,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9819999933242798,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9775999784469604,"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/computer-science","display_name":"Computer science","score":0.5984522104263306},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5068796277046204},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3851167559623718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3203234076499939},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05678468942642212}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5984522104263306},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5068796277046204},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3851167559623718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3203234076499939},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05678468942642212},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/make7010015","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7010015","pdf_url":"https://www.mdpi.com/2504-4990/7/1/15/pdf?version=1739184685","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1a9af9afb2f745fd973c64992323eb77","is_oa":true,"landing_page_url":"https://doaj.org/article/1a9af9afb2f745fd973c64992323eb77","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction, Vol 7, Iss 1, p 15 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/make7010015","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7010015","pdf_url":"https://www.mdpi.com/2504-4990/7/1/15/pdf?version=1739184685","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2114724169","display_name":null,"funder_award_id":"C1774095","funder_id":"https://openalex.org/F4320326762","funder_display_name":"Nemzeti Kutat\u00e1si Fejleszt\u00e9si \u00e9s Innov\u00e1ci\u00f3s Hivatal"},{"id":"https://openalex.org/G4222473055","display_name":null,"funder_award_id":"RRF-2.3.1-21-2022-00006","funder_id":"https://openalex.org/F4320326762","funder_display_name":"Nemzeti Kutat\u00e1si Fejleszt\u00e9si \u00e9s Innov\u00e1ci\u00f3s Hivatal"}],"funders":[{"id":"https://openalex.org/F4320326762","display_name":"Nemzeti Kutat\u00e1si Fejleszt\u00e9si \u00e9s Innov\u00e1ci\u00f3s Hivatal","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4407298138.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1548207260","https://openalex.org/W2123301721","https://openalex.org/W2180566385","https://openalex.org/W2913352150","https://openalex.org/W2964110616","https://openalex.org/W2970476646","https://openalex.org/W2970641574","https://openalex.org/W2970971581","https://openalex.org/W2979826702","https://openalex.org/W3095203335","https://openalex.org/W3174544005","https://openalex.org/W4389727268","https://openalex.org/W4391855109","https://openalex.org/W6632926901","https://openalex.org/W6682631176","https://openalex.org/W6779857854"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Generative":[0],"large":[1],"language":[2],"models":[3,82,112],"(LLMs)":[4],"have":[5],"revolutionized":[6],"the":[7,44,62,70,73,78,81,130,149,178],"development":[8],"of":[9,46,72,80,118,151,180],"knowledge-based":[10],"systems,":[11],"enabling":[12],"new":[13],"possibilities":[14],"in":[15,28,120,123,127,139,182],"applications":[16],"like":[17],"ChatGPT,":[18],"Bing,":[19],"and":[20,35,48,58,65,125,174],"Gemini.":[21],"Two":[22],"key":[23],"strategies":[24],"for":[25],"domain":[26],"adaptation":[27],"these":[29],"systems":[30,103],"are":[31],"Domain-Specific":[32],"Fine-Tuning":[33],"(DFT)":[34],"Retrieval-Augmented":[36],"Generation":[37],"(RAG).":[38],"In":[39],"this":[40],"study,":[41],"we":[42,165],"evaluate":[43,69],"performance":[45,71,79,162],"RAG":[47,111,153,181],"DFT":[49,114,133],"on":[50,95],"several":[51],"LLM":[52],"architectures,":[53],"including":[54],"GPT-J-6B,":[55],"OPT-6.7B,":[56],"LLaMA,":[57],"LLaMA-2.":[59],"We":[60,75,146],"use":[61],"ROUGE,":[63,121],"BLEU,":[64,124],"METEOR":[66],"scores":[67],"to":[68,161],"models.":[74],"also":[76,147],"measure":[77],"with":[83,108,154],"our":[84],"own":[85],"designed":[86],"cosine":[87],"similarity-based":[88],"Coverage":[89],"Score":[90],"(CS).":[91],"Our":[92],"results,":[93],"based":[94],"experiments":[96],"across":[97],"multiple":[98],"datasets,":[99],"show":[100],"that":[101,171],"RAG-based":[102,169],"consistently":[104],"outperform":[105,113],"those":[106],"fine-tuned":[107],"DFT.":[109],"Specifically,":[110],"by":[115],"an":[116],"average":[117],"17%":[119],"13%":[122],"36%":[126],"CS.":[128],"At":[129],"same":[131],"time,":[132],"achieves":[134],"only":[135],"a":[136,167],"modest":[137],"advantage":[138],"METEOR,":[140],"suggesting":[141],"slightly":[142],"better":[143],"creative":[144],"capabilities.":[145],"highlight":[148],"challenges":[150],"integrating":[152],"DFT,":[155],"as":[156],"such":[157],"integration":[158],"can":[159],"lead":[160],"degradation.":[163],"Furthermore,":[164],"propose":[166],"simplified":[168],"architecture":[170],"maximizes":[172],"efficiency":[173],"reduces":[175],"hallucination,":[176],"underscoring":[177],"advantages":[179],"building":[183],"reliable,":[184],"domain-adapted":[185],"knowledge":[186],"systems.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":18}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-02-10T00:00:00"}