{"id":"https://openalex.org/W4398233813","doi":"https://doi.org/10.1145/3626246.3654683","title":"Demystifying Data Management for Large Language Models","display_name":"Demystifying Data Management for Large Language Models","publication_year":2024,"publication_date":"2024-05-23","ids":{"openalex":"https://openalex.org/W4398233813","doi":"https://doi.org/10.1145/3626246.3654683"},"language":"en","primary_location":{"id":"doi:10.1145/3626246.3654683","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626246.3654683","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3626246.3654683","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015552951","display_name":"Xupeng Miao","orcid":"https://orcid.org/0000-0002-9371-8358"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xupeng Miao","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062437461","display_name":"Zhihao Jia","orcid":"https://orcid.org/0000-0002-1270-5185"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihao Jia","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062357883","display_name":"Bin Cui","orcid":"https://orcid.org/0000-0003-1681-4677"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Cui","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015552951"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":4.4105,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94968467,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"547","last_page":"555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9980000257492065,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9979000091552734,"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":0.7389824390411377},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.352489709854126},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3470379710197449},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3335241973400116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7389824390411377},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.352489709854126},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3470379710197449},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3335241973400116}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626246.3654683","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626246.3654683","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3626246.3654683","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626246.3654683","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W2437617937","https://openalex.org/W2549035799","https://openalex.org/W2612026221","https://openalex.org/W2612925715","https://openalex.org/W2734941459","https://openalex.org/W2799200478","https://openalex.org/W2971169561","https://openalex.org/W3014705052","https://openalex.org/W3029299514","https://openalex.org/W3037285953","https://openalex.org/W3081844508","https://openalex.org/W3082424964","https://openalex.org/W3085364681","https://openalex.org/W3123375411","https://openalex.org/W3137010024","https://openalex.org/W3148437589","https://openalex.org/W3154939421","https://openalex.org/W3172314079","https://openalex.org/W3173850788","https://openalex.org/W3174828871","https://openalex.org/W3175089547","https://openalex.org/W3177130063","https://openalex.org/W3177263144","https://openalex.org/W3177765786","https://openalex.org/W3196976833","https://openalex.org/W3198440572","https://openalex.org/W3205803342","https://openalex.org/W3206487987","https://openalex.org/W3213241618","https://openalex.org/W4205737716","https://openalex.org/W4220991771","https://openalex.org/W4221152111","https://openalex.org/W4224049479","https://openalex.org/W4226278401","https://openalex.org/W4245826835","https://openalex.org/W4281811562","https://openalex.org/W4281972940","https://openalex.org/W4282591925","https://openalex.org/W4286447321","https://openalex.org/W4289533987","https://openalex.org/W4310282800","https://openalex.org/W4312537169","https://openalex.org/W4312903631","https://openalex.org/W4312905556","https://openalex.org/W4321448343","https://openalex.org/W4321448364","https://openalex.org/W4323343904","https://openalex.org/W4364382874","https://openalex.org/W4367310643","https://openalex.org/W4376988980","https://openalex.org/W4383749415","https://openalex.org/W4385572845","https://openalex.org/W4385573090","https://openalex.org/W4385847487","https://openalex.org/W4386128198","https://openalex.org/W4386768680","https://openalex.org/W4386768923","https://openalex.org/W4387321091","https://openalex.org/W4389519618","https://openalex.org/W4389520460","https://openalex.org/W4389524288","https://openalex.org/W4389539730","https://openalex.org/W4394998727","https://openalex.org/W6600175266","https://openalex.org/W6600281192","https://openalex.org/W6600310816","https://openalex.org/W6600351811","https://openalex.org/W6600388300","https://openalex.org/W6600757733","https://openalex.org/W6602555712","https://openalex.org/W6605363982","https://openalex.org/W6606250760","https://openalex.org/W6606545560","https://openalex.org/W6630858386","https://openalex.org/W6815619692"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Navigating":[0],"the":[1,7,34,41,64,69,84,98],"intricacies":[2],"of":[3,9,37,46,54,57],"data":[4,22,38,62,91],"management":[5,23,39,92],"in":[6,90],"era":[8],"Large":[10],"Language":[11],"Models":[12],"(LLMs)":[13],"presents":[14],"both":[15],"challenges":[16,89],"and":[17,21,43,60,73,87,102],"opportunities":[18],"for":[19,93],"database":[20],"communities.":[24],"In":[25],"this":[26,105],"tutorial,":[27],"we":[28],"offer":[29,79],"a":[30],"comprehensive":[31],"exploration":[32],"into":[33,83],"vital":[35],"role":[36],"across":[40],"development":[42],"deployment":[44],"phases":[45],"advanced":[47],"LLMs.":[48],"We":[49],"provide":[50],"an":[51],"in-depth":[52],"survey":[53],"existing":[55],"techniques":[56],"managing":[58],"knowledge":[59,99],"parameter":[61],"during":[63],"whole":[65],"LLM":[66],"lifecycle,":[67],"emphasizing":[68],"balance":[70],"between":[71],"efficiency":[72],"effectiveness.":[74],"This":[75],"tutorial":[76],"stands":[77],"to":[78,100,104],"participants":[80],"valuable":[81],"insights":[82],"best":[85],"practices":[86],"contemporary":[88],"LLMs,":[94],"equipping":[95],"them":[96],"with":[97],"navigate":[101],"contribute":[103],"rapidly":[106],"evolving":[107],"field.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}