{"id":"https://openalex.org/W7151439514","doi":"https://doi.org/10.1145/3786703","title":"The Case For Language Model Approximated LIKE Predicate","display_name":"The Case For Language Model Approximated LIKE Predicate","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7151439514","doi":"https://doi.org/10.1145/3786703"},"language":"en","primary_location":{"id":"doi:10.1145/3786703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786703","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3786703","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017403079","display_name":"Y. X. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingze Li","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0005-9035-7218","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133102920","display_name":"Dong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0008-3755-6412","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133132035","display_name":"Zixuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Wang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0006-3896-9847","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133071979","display_name":"Yingli Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingli Zhou","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-5630-6822","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Yan","orcid":"https://orcid.org/0000-0002-2078-3343"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Yan","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-2078-3343","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Geng","orcid":"https://orcid.org/0009-0003-0964-585X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Geng","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0003-0964-585X","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyue Wang","orcid":"https://orcid.org/0009-0009-9792-4309"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyue Wang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0009-9792-4309","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziqing Zeng","orcid":"https://orcid.org/0009-0007-3930-0675"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqing Zeng","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0007-3930-0675","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hongzhi Wang","orcid":"https://orcid.org/0000-0002-7521-2871"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Wang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-7521-2871","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40913434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":"1","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.2842999994754791,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.2842999994754791,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.28049999475479126,"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/T10028","display_name":"Topic Modeling","score":0.15629999339580536,"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/language-model","display_name":"Language model","score":0.7141000032424927},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.6832000017166138},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.5866000056266785},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4943999946117401},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4348999857902527},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.41440001130104065},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.37290000915527344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531999945640564},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7141000032424927},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.6832000017166138},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.46720001101493835},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41620001196861267},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.41440001130104065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4016000032424927},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32989999651908875},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2590000033378601},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786703","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3786703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786703","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1984057771","https://openalex.org/W2016995838","https://openalex.org/W2038941723","https://openalex.org/W2046298800","https://openalex.org/W2047396520","https://openalex.org/W2055261195","https://openalex.org/W2060277733","https://openalex.org/W2065259291","https://openalex.org/W2084538728","https://openalex.org/W2087721273","https://openalex.org/W2102337021","https://openalex.org/W2107293766","https://openalex.org/W2123020735","https://openalex.org/W2129750215","https://openalex.org/W2138662031","https://openalex.org/W2139660688","https://openalex.org/W2147805208","https://openalex.org/W2150871235","https://openalex.org/W2157233202","https://openalex.org/W2236116266","https://openalex.org/W2550821151","https://openalex.org/W2560647685","https://openalex.org/W2750620035","https://openalex.org/W2768381684","https://openalex.org/W2798277312","https://openalex.org/W2948233700","https://openalex.org/W2962771342","https://openalex.org/W2991530444","https://openalex.org/W3004034804","https://openalex.org/W3029541804","https://openalex.org/W3030764521","https://openalex.org/W3032789239","https://openalex.org/W3080797093","https://openalex.org/W3095849853","https://openalex.org/W3097225903","https://openalex.org/W3098605233","https://openalex.org/W3127228978","https://openalex.org/W3129744650","https://openalex.org/W3152698349","https://openalex.org/W3164254023","https://openalex.org/W3210277894","https://openalex.org/W4226086155","https://openalex.org/W4283319958","https://openalex.org/W4290742115","https://openalex.org/W4317639412","https://openalex.org/W4317767740","https://openalex.org/W4321648953","https://openalex.org/W4367047159","https://openalex.org/W4379382789","https://openalex.org/W4385565351","https://openalex.org/W4387559950","https://openalex.org/W4387667125","https://openalex.org/W4393158884","https://openalex.org/W4393180046","https://openalex.org/W4393180053","https://openalex.org/W4398233983","https://openalex.org/W4402043003","https://openalex.org/W4402043038","https://openalex.org/W4404782964","https://openalex.org/W4407355910"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"databases":[1,93],"often":[2],"use":[3],"the":[4,13,20,175],"LIKE":[5,66,148,164,198,211],"predicate":[6],"to":[7,26,31,45,105,173,218],"search":[8,14,22],"text":[9],"data.":[10],"However,":[11,89],"when":[12],"condition":[15],"is":[16],"interrupted":[17],"by":[18,212],"wildcards,":[19],"existing":[21],"structure":[23],"can":[24,63],"degrade":[25],"a":[27,58,69,116,142,184],"worst-case":[28],"complexity":[29,159],"linear":[30],"full":[32],"table":[33,84],"scale,":[34],"resulting":[35],"in":[36,54,79],"poor":[37],"performance.":[38],"Traditional":[39],"methods,":[40],"such":[41,96],"as":[42,97,141],"B+-trees,":[43],"fail":[44],"handle":[46],"wildcards":[47],"at":[48],"both":[49],"ends":[50],"efficiently.":[51],"Recent":[52],"advances":[53],"language":[55,119,194,220],"models":[56,62,221],"offer":[57],"promising":[59],"solution.":[60],"These":[61],"decode":[64],"complex":[65,147],"patterns":[67,149],"into":[68,92,150],"small":[70,134],"set":[71],"of":[72,177,189,215,234],"candidate":[73],"values,":[74],"which":[75],"are":[76],"then":[77],"verified":[78],"dataset-size-invariant":[80],"time":[81],"via":[82],"hash":[83],"lookups,":[85],"greatly":[86],"improving":[87],"efficiency.":[88],"integrating":[90],"LLMs":[91],"faces":[94],"challenges":[95],"high":[98,206],"latency,":[99],"large":[100,193,219],"storage":[101],"requirements,":[102],"and":[103,201,222,231,247],"sensitivity":[104],"data":[106,246],"distribution":[107,249],"drifts.":[108,250],"To":[109],"address":[110],"these":[111],"issues,":[112],"we":[113],"propose":[114],"SMILE,":[115,182],"S":[117],"mall":[118],"M":[120],"odel":[121],"I":[122],"ntegrated":[123],"L":[124],"IKE":[125],"E":[126],"ngine":[127],"that":[128,145],"learns":[129],"column-local":[130],"character":[131],"distributions":[132],"through":[133],"but":[135],"exquisite":[136],"parameters.":[137],"Our":[138,155,180],"SMILE":[139,204],"acts":[140],"neural":[143],"translator":[144],"converts":[146],"their":[151],"corresponding":[152],"result":[153],"sets.":[154],"approach":[156],"achieves":[157,196],"asymptotic":[158],"improvements":[160],"while":[161,209],"preserving":[162],"SQL":[163],"logic.":[165],"We":[166],"conduct":[167],"comprehensive":[168],"evaluation":[169],"across":[170],"diverse":[171],"datasets":[172],"validate":[174],"efficacy":[176],"our":[178,240],"approach.":[179],"compact":[181],"with":[183],"parameter":[185],"size":[186],"5":[187],"orders":[188,214,233],"magnitude":[190,216,235],"smaller":[191],"than":[192,228,237],"models,":[195],"strong":[197],"decoding":[199],"efficiency":[200],"quality.":[202],"Specifically,":[203],"obtains":[205],"recall":[207],"ability":[208],"accelerating":[210],"3":[213],"compared":[217],"sequential":[223],"scans,":[224],"1.8-41.6":[225],"times":[226],"faster":[227,236],"trigram":[229],"indexes,":[230],"2":[232],"B+-trees.":[238],"Moreover,":[239],"model":[241],"demonstrates":[242],"robustness":[243],"against":[244],"potential":[245],"query":[248]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-04-08T00:00:00"}