{"id":"https://openalex.org/W4391094932","doi":"https://doi.org/10.1109/bigdata59044.2023.10386472","title":"LLMs with User-defined Prompts as Generic Data Operators for Reliable Data Processing","display_name":"LLMs with User-defined Prompts as Generic Data Operators for Reliable Data Processing","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391094932","doi":"https://doi.org/10.1109/bigdata59044.2023.10386472"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013776504","display_name":"Luyi Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luyi Ma","raw_affiliation_strings":["Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1330693074"]},{"raw_affiliation_string":"Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058472868","display_name":"Nikhil Thakurdesai","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhil Thakurdesai","raw_affiliation_strings":["Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1330693074"]},{"raw_affiliation_string":"Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441171","display_name":"Jiao Chen","orcid":"https://orcid.org/0000-0003-2367-4369"},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiao Chen","raw_affiliation_strings":["Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1330693074"]},{"raw_affiliation_string":"Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034805091","display_name":"Jianpeng Xu","orcid":"https://orcid.org/0000-0002-9500-3700"},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianpeng Xu","raw_affiliation_strings":["Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1330693074"]},{"raw_affiliation_string":"Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025613254","display_name":"Evren K\u00f6rpeo\u011flu","orcid":null},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evren Korpeoglu","raw_affiliation_strings":["Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1330693074"]},{"raw_affiliation_string":"Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101853574","display_name":"Sushant Kumar","orcid":"https://orcid.org/0000-0001-9935-6936"},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sushant Kumar","raw_affiliation_strings":["Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1330693074"]},{"raw_affiliation_string":"Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079669827","display_name":"Kannan Achan","orcid":"https://orcid.org/0009-0000-9186-3175"},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kannan Achan","raw_affiliation_strings":["Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech,Personalization Team,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1330693074"]},{"raw_affiliation_string":"Personalization Team, Walmart Global Tech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1330693074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5013776504"],"corresponding_institution_ids":["https://openalex.org/I1330693074"],"apc_list":null,"apc_paid":null,"fwci":1.5632,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83432852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3144","last_page":"3148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9952999949455261,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9769999980926514,"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":0.6774656772613525},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.41650551557540894},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3334752321243286},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25553467869758606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6774656772613525},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.41650551557540894},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3334752321243286},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25553467869758606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2542459869","https://openalex.org/W2892181857","https://openalex.org/W2962804639","https://openalex.org/W3040266635","https://openalex.org/W3135550350","https://openalex.org/W3168867926","https://openalex.org/W4283026156","https://openalex.org/W4292779060","https://openalex.org/W4304194220","https://openalex.org/W4308547963","https://openalex.org/W4377090137","https://openalex.org/W4378464611","https://openalex.org/W4378509449","https://openalex.org/W4384918448","https://openalex.org/W4385571011","https://openalex.org/W4385890089","https://openalex.org/W4387724821","https://openalex.org/W4389523706","https://openalex.org/W4391136507","https://openalex.org/W4393141466","https://openalex.org/W6612627285","https://openalex.org/W6778883912","https://openalex.org/W6796581206","https://openalex.org/W6838461927","https://openalex.org/W6845413636","https://openalex.org/W6845816046","https://openalex.org/W6852505888","https://openalex.org/W6852738809","https://openalex.org/W6853251322","https://openalex.org/W6854692045","https://openalex.org/W6854866820","https://openalex.org/W6855780230","https://openalex.org/W6856674126","https://openalex.org/W6857776163"],"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":{"Data":[0],"processing":[1,29,113,155,166],"is":[2],"one":[3],"of":[4,17,183],"the":[5,18,21,33,42,100,111,134,137,146,149,171],"fundamental":[6],"steps":[7],"in":[8,30,163],"machine":[9,46],"learning":[10,47],"pipelines":[11,48],"to":[12,53,109,132,178],"ensure":[13],"data":[14,28,85,90,112,143,154,165],"quality.":[15],"Majority":[16],"applications":[19],"consider":[20],"user-defined":[22,104],"function":[23],"(UDF)":[24],"design":[25,35,55,73,102,185],"pattern":[26,36,56,74,186],"for":[27,88,187],"databases.":[31],"Although":[32],"UDF":[34],"introduces":[37],"flexibility,":[38],"reusability":[39],"and":[40,62,93,173],"scalability,":[41],"increasing":[43],"demand":[44],"on":[45,148],"brings":[49],"three":[50],"new":[51,72],"challenges":[52,172],"this":[54,184],"\u2013":[57],"not":[58,60,63],"low-code,":[59],"dependency-free":[61],"knowledge-aware.":[64,156],"To":[65],"address":[66],"these":[67,159],"challenges,":[68],"we":[69,169],"propose":[70],"a":[71,83,119,180],"that":[75],"large":[76],"language":[77],"models":[78],"(LLMs)":[79],"could":[80,144],"work":[81],"as":[82],"generic":[84],"operator":[86],"(LLM-GDO)":[87],"reliable":[89],"cleansing,":[91],"transformation":[92],"modeling":[94],"with":[95,118,141,161],"their":[96],"human-compatible":[97],"performance.":[98],"In":[99],"LLM-GDO":[101],"pattern,":[103],"prompts":[105],"(UDPs)":[106],"are":[107],"used":[108],"represent":[110],"logic":[114],"rather":[115],"than":[116],"implementations":[117],"specific":[120],"programming":[121],"language.":[122],"LLMs":[123,140,177],"can":[124],"be":[125],"centrally":[126],"maintained":[127],"so":[128],"users":[129],"don\u2019t":[130],"have":[131],"manage":[133],"dependencies":[135],"at":[136],"run-time.":[138],"Fine-tuning":[139],"domain-specific":[142,150],"enhance":[145],"performance":[147],"tasks":[151],"which":[152],"makes":[153],"We":[157],"illustrate":[158],"advantages":[160],"examples":[162],"different":[164],"tasks.":[167],"Furthermore,":[168],"summarize":[170],"opportunities":[174],"introduced":[175],"by":[176],"provide":[179],"complete":[181],"view":[182],"more":[188],"discussions.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-12T23:16:27.785689","created_date":"2025-10-10T00:00:00"}