{"id":"https://openalex.org/W4399261722","doi":"https://doi.org/10.1145/3663741.3664785","title":"Are Large Language Models the New Interface for Data Pipelines?","display_name":"Are Large Language Models the New Interface for Data Pipelines?","publication_year":2024,"publication_date":"2024-06-01","ids":{"openalex":"https://openalex.org/W4399261722","doi":"https://doi.org/10.1145/3663741.3664785"},"language":"en","primary_location":{"id":"doi:10.1145/3663741.3664785","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3663741.3664785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Workshop on Big Data in Emergent Distributed Environments","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ris.utwente.nl/ws/files/479541070/3663741.3664785.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004953377","display_name":"Sylvio Barbon","orcid":"https://orcid.org/0000-0002-4988-0702"},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Sylvio Barbon Junior","raw_affiliation_strings":["Universita degli Studi di Trieste, Italy"],"raw_orcid":"https://orcid.org/0000-0002-4988-0702","affiliations":[{"raw_affiliation_string":"Universita degli Studi di Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030929146","display_name":"Paolo Ceravolo","orcid":"https://orcid.org/0000-0002-4519-0173"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Ceravolo","raw_affiliation_strings":["University of Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0002-4519-0173","affiliations":[{"raw_affiliation_string":"University of Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029547855","display_name":"Sven Groppe","orcid":"https://orcid.org/0000-0001-5196-1117"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Groppe","raw_affiliation_strings":["University of L\u00fcbeck, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5196-1117","affiliations":[{"raw_affiliation_string":"University of L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050418400","display_name":"Mustafa Jarrar","orcid":"https://orcid.org/0000-0003-4351-4207"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]},{"id":"https://openalex.org/I94800806","display_name":"Birzeit University","ror":"https://ror.org/0256kw398","country_code":"PS","type":"education","lineage":["https://openalex.org/I94800806"]}],"countries":["BE","PS"],"is_corresponding":false,"raw_author_name":"Mustafa Jarrar","raw_affiliation_strings":["Birzeit University, Palestine","VUB - Vrije Universiteit Brussel [Bruxelles] (Pleinlaan 2, 1050 Brussel - Belgium)"],"raw_orcid":"https://orcid.org/0000-0003-4351-4207","affiliations":[{"raw_affiliation_string":"Birzeit University, Palestine","institution_ids":["https://openalex.org/I94800806"]},{"raw_affiliation_string":"VUB - Vrije Universiteit Brussel [Bruxelles] (Pleinlaan 2, 1050 Brussel - Belgium)","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002165190","display_name":"Samira Maghool","orcid":"https://orcid.org/0000-0001-8310-2050"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Samira Maghool","raw_affiliation_strings":["University of Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8310-2050","affiliations":[{"raw_affiliation_string":"University of Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050812414","display_name":"Florence S\u00e8des","orcid":"https://orcid.org/0000-0002-9273-302X"},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Florence S\u00e8des","raw_affiliation_strings":["University Toulouse 3 Paul Sabatier, France"],"raw_orcid":"https://orcid.org/0000-0002-9273-302X","affiliations":[{"raw_affiliation_string":"University Toulouse 3 Paul Sabatier, France","institution_ids":["https://openalex.org/I134560555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039032451","display_name":"Soror Sahri","orcid":"https://orcid.org/0000-0002-1554-7565"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Soror Sahri","raw_affiliation_strings":["Universit\u00e9 Paris Cit\u00e9, France"],"raw_orcid":"https://orcid.org/0000-0002-1554-7565","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, France","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062035687","display_name":"Maurice van Keulen","orcid":"https://orcid.org/0000-0003-2436-1372"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maurice Van Keulen","raw_affiliation_strings":["University of Twente, The Netherlands","University of Twente (Drienerlolaan 5, 7522 NB Enschede - Netherlands)"],"raw_orcid":"https://orcid.org/0000-0003-2436-1372","affiliations":[{"raw_affiliation_string":"University of Twente, The Netherlands","institution_ids":["https://openalex.org/I94624287"]},{"raw_affiliation_string":"University of Twente (Drienerlolaan 5, 7522 NB Enschede - Netherlands)","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":6,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5004953377"],"corresponding_institution_ids":["https://openalex.org/I142444530"],"apc_list":null,"apc_paid":null,"fwci":2.8137,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91485125,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9991000294685364,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9923999905586243,"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/T11719","display_name":"Data Quality and Management","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7821980118751526},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6656349301338196},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.5612108111381531},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5306801795959473},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5171108245849609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45840007066726685},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43758925795555115},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4228409230709076},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4112808108329773},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3253825902938843},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.21296989917755127},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14298012852668762},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10244455933570862}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821980118751526},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6656349301338196},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.5612108111381531},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5306801795959473},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5171108245849609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45840007066726685},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43758925795555115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4228409230709076},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4112808108329773},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3253825902938843},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.21296989917755127},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14298012852668762},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10244455933570862},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3663741.3664785","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3663741.3664785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Workshop on Big Data in Emergent Distributed Environments","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire/4c56805c-956d-4535-b8c7-fba0cea65583","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/4c56805c-956d-4535-b8c7-fba0cea65583","pdf_url":"https://ris.utwente.nl/ws/files/479541070/3663741.3664785.pdf","source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Barbon, S, Ceravolo, P, Groppe, S, Jarrar, M, Maghool, S, S\u00e8des, F, Sahri, S & Van Keulen, M 2024, Are Large Language Models the New Interface for Data Pipelines? in P Cudre-Mauroux, A Ko & R Wrembel (eds), Proceedings of the International Workshop on Big Data in Emergent Distributed Environments, BIDEDE 2024, in conjunction with the 2024 ACM SIGMOD/PODS Conference., 6, Proceedings of the International Workshop on Big Data in Emergent Distributed Environments, BIDEDE 2024, in conjunction with the 2024 ACM SIGMOD/PODS Conference, Association for Computing Machinery, 2024 International Workshop on Big Data in Emergent Distributed Environments, BiDEDE 2024, Santiago, Chile, 9/06/24. https://doi.org/10.1145/3663741.3664785","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:HAL:hal-04710473v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04710473","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SIGMOD/PODS '24: International Conference on Management of Data, Jun 2024, Santiago AA Chile, France. pp.1-6, &#x27E8;10.1145/3663741.3664785&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:arts.units.it:11368/3115679","is_oa":false,"landing_page_url":"https://hdl.handle.net/11368/3115679","pdf_url":null,"source":{"id":"https://openalex.org/S4306400480","display_name":"ArTS Archivio della ricerca di Trieste (University of Trieste https://www.units.it/)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142444530","host_organization_name":"University of Trieste","host_organization_lineage":["https://openalex.org/I142444530"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:ris.utwente.nl:openaire/4c56805c-956d-4535-b8c7-fba0cea65583","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/4c56805c-956d-4535-b8c7-fba0cea65583","pdf_url":"https://ris.utwente.nl/ws/files/479541070/3663741.3664785.pdf","source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Barbon, S, Ceravolo, P, Groppe, S, Jarrar, M, Maghool, S, S\u00e8des, F, Sahri, S & Van Keulen, M 2024, Are Large Language Models the New Interface for Data Pipelines? in P Cudre-Mauroux, A Ko & R Wrembel (eds), Proceedings of the International Workshop on Big Data in Emergent Distributed Environments, BIDEDE 2024, in conjunction with the 2024 ACM SIGMOD/PODS Conference., 6, Proceedings of the International Workshop on Big Data in Emergent Distributed Environments, BIDEDE 2024, in conjunction with the 2024 ACM SIGMOD/PODS Conference, Association for Computing Machinery, 2024 International Workshop on Big Data in Emergent Distributed Environments, BiDEDE 2024, Santiago, Chile, 9/06/24. https://doi.org/10.1145/3663741.3664785","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399261722.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2602144787","https://openalex.org/W2803200182","https://openalex.org/W2966284335","https://openalex.org/W3010336026","https://openalex.org/W3112520120","https://openalex.org/W4213308398","https://openalex.org/W4221143046","https://openalex.org/W4282915085","https://openalex.org/W4313558118","https://openalex.org/W4321786089","https://openalex.org/W4375869868","https://openalex.org/W4386128198","https://openalex.org/W4387494819","https://openalex.org/W4387789903","https://openalex.org/W4390692489","https://openalex.org/W6810539046","https://openalex.org/W6854692045"],"related_works":["https://openalex.org/W2365169615","https://openalex.org/W1970538215","https://openalex.org/W2400151637","https://openalex.org/W2975827637","https://openalex.org/W2354089692","https://openalex.org/W595497825","https://openalex.org/W4236323843","https://openalex.org/W2002616876","https://openalex.org/W3174418441","https://openalex.org/W4309298167"],"abstract_inverted_index":{"A":[0],"Language":[1,20],"Model":[2],"is":[3],"a":[4,43,105,148],"term":[5],"that":[6],"encompasses":[7],"various":[8,74],"types":[9],"of":[10,46,54,126,151],"models":[11,94],"designed":[12],"to":[13,28,31,109,135],"understand":[14],"and":[15,37,60,67,86,99,138,153,158],"generate":[16],"human":[17],"communication.":[18],"Large":[19],"Models":[21],"(LLMs)":[22],"have":[23],"gained":[24],"significant":[25],"attention":[26],"due":[27],"their":[29,64],"ability":[30],"process":[32],"text":[33],"with":[34,63],"human-like":[35],"fluency":[36],"coherence,":[38],"making":[39],"them":[40],"valuable":[41,97],"for":[42],"wide":[44,149],"range":[45,150],"data-related":[47],"tasks":[48],"fashioned":[49],"as":[50,110],"pipelines.":[51],"The":[52],"capabilities":[53],"LLMs":[55],"in":[56,123,144],"natural":[57],"language":[58],"understanding":[59],"generation,":[61],"combined":[62],"scalability,":[65],"versatility,":[66],"state-of-the-art":[68],"performance,":[69],"enable":[70],"innovative":[71],"applications":[72,152],"across":[73,147],"AI-related":[75],"fields,":[76],"including":[77],"eXplainable":[78],"Artificial":[79],"Intelligence":[80],"(XAI),":[81],"Automated":[82],"Machine":[83],"Learning":[84],"(AutoML),":[85],"Knowledge":[87],"Graphs":[88],"(KG).":[89],"Furthermore,":[90],"we":[91,119],"believe":[92],"these":[93,130],"can":[95,133],"extract":[96],"insights":[98],"make":[100],"data-driven":[101],"decisions":[102],"at":[103],"scale,":[104],"practice":[106],"commonly":[107],"referred":[108],"Big":[111],"Data":[112],"Analytics":[113],"(BDA).":[114],"In":[115],"this":[116],"position":[117],"paper,":[118],"provide":[120],"some":[121],"discussions":[122],"the":[124],"direction":[125],"unlocking":[127],"synergies":[128],"among":[129],"technologies,":[131],"which":[132],"lead":[134],"more":[136],"powerful":[137],"intelligent":[139],"AI":[140],"solutions,":[141],"driving":[142],"improvements":[143],"data":[145],"pipelines":[146],"domains":[154],"integrating":[155],"humans,":[156],"computers,":[157],"knowledge.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}
