{"id":"https://openalex.org/W7219920862","doi":null,"title":"Large Language Models in Modern Data Engineering: A Systematic Review of Architectures, Use Cases, and Limitations","display_name":"Large Language Models in Modern Data Engineering: A Systematic Review of Architectures, Use Cases, and Limitations","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W7219920862"},"language":"en","primary_location":{"id":"pmh:oai:ojs2.ijbcs.org:article/14","doi":null,"is_oa":true,"landing_page_url":"https://ijbcs.org/index.php/IJBCS/article/view/2023-03","pdf_url":"https://ijbcs.org/index.php/IJBCS/article/download/2023-03/2023-03","source":{"id":"https://openalex.org/S7407079900","display_name":"International Journal of Business & Computational Science","issn_l":"3080-3748","issn":["3080-3748","3080-3756"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3080-3748","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"review","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ijbcs.org/index.php/IJBCS/article/download/2023-03/2023-03","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102391405","display_name":"Shambhu Adhikari","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Adhikari, Shambhu","raw_affiliation_strings":["Sr. Data Engineer - United  Airlines, NW, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sr. Data Engineer - United  Airlines, NW, NJ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5102391405"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"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":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8417999744415283,"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":0.8417999744415283,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.032499998807907104,"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/T10260","display_name":"Software Engineering Research","score":0.02199999988079071,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":1.0},{"id":"https://openalex.org/keywords/data-engineering","display_name":"data engineering","score":0.9850000143051147},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.996999979019165},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.6809999942779541},{"id":"https://openalex.org/keywords/tool-calling","display_name":"tool calling","score":0.5370000004768372},{"id":"https://openalex.org/keywords/hallucinations","display_name":"hallucinations","score":0.6309999823570251},{"id":"https://openalex.org/keywords/data-governance","display_name":"data governance","score":0.7950000166893005},{"id":"https://openalex.org/keywords/data-quality-monitoring","display_name":"data quality monitoring","score":0.8320000171661377},{"id":"https://openalex.org/keywords/schema-inference","display_name":"schema inference","score":0.8759999871253967},{"id":"https://openalex.org/keywords/metadata-creation","display_name":"metadata generation","score":0.75},{"id":"https://openalex.org/keywords/data-ingestion","display_name":"data ingestion","score":0.5360000133514404},{"id":"https://openalex.org/keywords/explainability","display_name":"explainability","score":0.7870000004768372},{"id":"https://openalex.org/keywords/privacy","display_name":"privacy","score":0.7429999709129333},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.7599999904632568},{"id":"https://openalex.org/keywords/data-platform-architecture","display_name":"data platform architecture","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.723800003528595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7021999955177307},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5634999871253967},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.476500004529953},{"id":"https://openalex.org/C196879817","wikidata":"https://www.wikidata.org/wiki/Q872685","display_name":"Data governance","level":4,"score":0.43959999084472656},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4275999963283539},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.3840999901294708},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C509989072","wikidata":"https://www.wikidata.org/wiki/Q15188241","display_name":"Model-driven architecture","level":4,"score":0.35350000858306885},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C39389867","wikidata":"https://www.wikidata.org/wiki/Q380767","display_name":"Corporate governance","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.3116999864578247},{"id":"https://openalex.org/C2779791154","wikidata":"https://www.wikidata.org/wiki/Q258040","display_name":"Model transformation","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C126082660","wikidata":"https://www.wikidata.org/wiki/Q4252370","display_name":"Digital transformation","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C98143201","wikidata":"https://www.wikidata.org/wiki/Q1147639","display_name":"Data dictionary","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:ojs2.ijbcs.org:article/14","doi":null,"is_oa":true,"landing_page_url":"https://ijbcs.org/index.php/IJBCS/article/view/2023-03","pdf_url":"https://ijbcs.org/index.php/IJBCS/article/download/2023-03/2023-03","source":{"id":"https://openalex.org/S7407079900","display_name":"International Journal of Business & Computational Science","issn_l":"3080-3748","issn":["3080-3748","3080-3756"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3080-3748","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:ojs2.ijbcs.org:article/14","doi":null,"is_oa":true,"landing_page_url":"https://ijbcs.org/index.php/IJBCS/article/view/2023-03","pdf_url":"https://ijbcs.org/index.php/IJBCS/article/download/2023-03/2023-03","source":{"id":"https://openalex.org/S7407079900","display_name":"International Journal of Business & Computational Science","issn_l":"3080-3748","issn":["3080-3748","3080-3756"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3080-3748","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[{"display_name":"Systematic Review","id":"https://openalex.org/study-designs/systematic-review"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7219920862.pdf","grobid_xml":"https://content.openalex.org/works/W7219920862.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2613597870","https://openalex.org/W2950067395","https://openalex.org/W3021338988","https://openalex.org/W3156891177","https://openalex.org/W3177813494","https://openalex.org/W3195577433","https://openalex.org/W4225405251","https://openalex.org/W4304195432","https://openalex.org/W4309395891"],"related_works":["https://openalex.org/W7116737435","https://openalex.org/W7220096768","https://openalex.org/W7221316170","https://openalex.org/W4410918002","https://openalex.org/W7125274441","https://openalex.org/W7119367023","https://openalex.org/W4396669430","https://openalex.org/W7138390671","https://openalex.org/W4411921758","https://openalex.org/W7156698190"],"abstract_inverted_index":{"Background":[0],"and":[1,28,41,54,80,83,116,132,161,168,177,187,190,206,231,240,249,287,296,303],"Purpose:":[2],"Large":[3],"language":[4],"models":[5],"(LLMs)":[6],"are":[7,253],"increasingly":[8],"integrated":[9],"into":[10,201],"modern":[11],"data":[12,16,25,111,199,214,228,263],"engineering":[13,200,215],"workflows,":[14],"including":[15],"ingestion,":[17],"schema":[18],"inference,":[19],"metadata":[20,160],"generation,":[21,159],"transformation":[22,157],"logic":[23],"synthesis,":[24,144],"quality":[26],"monitoring,":[27,286],"natural-language":[29,227],"interaction":[30],"with":[31,58,210],"analytical":[32],"systems.":[33],"Their":[34],"probabilistic":[35],"behavior":[36],"introduces":[37],"new":[38],"reliability,":[39,301],"governance,":[40],"reproducibility":[42],"concerns.":[43],"This":[44,195],"review":[45,65,120,196],"examines":[46],"the":[47,87,91,137,142,147,213],"architectural":[48,204,239,294],"patterns,":[49],"practical":[50,114],"data-engineering":[51],"use":[52,154],"cases,":[53],"operational":[55,304],"limitations":[56,182],"associated":[57],"LLM":[59,123,235],"integration.":[60],"Methods:":[61],"A":[62],"PRISMA-informed":[63],"systematic":[64],"was":[66,94,146],"conducted":[67],"across":[68],"IEEE":[69],"Xplore,":[70],"ACM":[71],"Digital":[72],"Library,":[73],"Scopus,":[74],"Web":[75],"of":[76,212],"Science,":[77],"PubMed,":[78],"arXiv,":[79],"selected":[81],"industrial":[82],"technical":[84],"reports.":[85],"For":[86],"historical":[88],"2023":[89],"edition,":[90],"evidence":[92],"window":[93],"restricted":[95],"to":[96,109,233],"studies":[97],"available":[98],"from":[99],"January":[100],"through":[101],"November":[102],"2022.":[103],"Sources":[104],"were":[105],"screened":[106],"for":[107,271],"relevance":[108],"LLM-enabled":[110,198],"engineering,":[112],"architecture,":[113,151],"deployment,":[115],"governance.":[117],"Findings:":[118],"The":[119],"identifies":[121],"direct":[122],"integration,":[124],"Retrieval-Augmented":[125],"Generation":[126],"(RAG),":[127],"agent-based":[128],"or":[129],"tool-calling":[130],"systems,":[131],"hybrid":[133],"governed":[134],"architectures":[135],"as":[136,237,256,267],"principal":[138],"integration":[139],"patterns.":[140],"Across":[141],"source":[143],"RAG":[145],"most":[148,254],"frequently":[149],"reported":[150],"while":[152,180],"common":[153],"cases":[155],"included":[156,173],"code":[158],"documentation":[162],"support,":[163],"conversational":[164],"analytics,":[165],"ingestion":[166],"assistance,":[167],"governance-oriented":[169],"checks.":[170],"Reported":[171],"benefits":[172],"productivity,":[174],"accessibility,":[175],"flexibility,":[176],"knowledge":[178],"reuse,":[179],"recurring":[181],"involved":[183],"hallucination,":[184],"privacy,":[185],"cost":[186,285],"scalability,":[188],"explainability,":[189],"governance":[191,241,297],"gaps.":[192],"Theoretical":[193],"Contributions:":[194],"organizes":[197],"a":[202,245],"structured":[203],"taxonomy":[205],"links":[207],"deployment":[208],"patterns":[209],"stages":[211],"lifecycle.":[216],"It":[217],"integrates":[218],"foundational":[219],"work":[220],"on":[221],"transformers,":[222],"retrieval,":[223],"production":[224,272],"machine":[225],"learning,":[226],"interfaces,":[229],"security,":[230],"explainability":[232],"frame":[234],"adoption":[236,291],"an":[238],"problem":[242],"rather":[243,265],"than":[244,266],"model-only":[246],"problem.":[247],"Conclusions":[248],"Policy":[250],"Implications:":[251],"LLMs":[252],"appropriate":[255],"governed,":[257],"assistive":[258],"components":[259],"embedded":[260],"within":[261],"deterministic":[262],"platforms":[264],"fully":[268],"autonomous":[269],"replacements":[270],"pipelines.":[273],"Organizations":[274],"should":[275],"prioritize":[276],"retrieval":[277],"grounding,":[278],"human":[279],"validation,":[280],"access":[281],"control,":[282],"lineage,":[283],"observability,":[284],"privacy":[288],"safeguards.":[289],"Responsible":[290],"requires":[292],"explicit":[293],"boundaries":[295],"mechanisms":[298],"that":[299],"preserve":[300],"auditability,":[302],"control.":[305]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-05T00:00:00"}