{"id":"https://openalex.org/W7133533088","doi":"https://doi.org/10.48550/arxiv.2603.02537","title":"Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis","display_name":"Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133533088","doi":"https://doi.org/10.48550/arxiv.2603.02537"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.02537","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02537","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.02537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128053994","display_name":"Yunxiang Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Su, Yunxiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022320856","display_name":"Tianjing Zeng","orcid":"https://orcid.org/0000-0003-3436-9060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Tianjing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128123661","display_name":"Zhongjun Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Zhongjun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102997976","display_name":"Lin Yin","orcid":"https://orcid.org/0000-0003-3604-506X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Yin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128061309","display_name":"Rong Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Rong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118903981","display_name":"Zhewei Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Zhewei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128101551","display_name":"Bolin Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Bolin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128089054","display_name":"Jingren Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jingren","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5128053994"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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":0.5396000146865845,"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":0.5396000146865845,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.07609999924898148,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.06679999828338623,"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/operand","display_name":"Operand","score":0.6638000011444092},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5564000010490417},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5358999967575073},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5236999988555908},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5194000005722046},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.45339998602867126},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.45019999146461487},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4300999939441681}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785000205039978},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.6638000011444092},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5564000010490417},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.35530000925064087},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.3521000146865845},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.313400000333786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.02537","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02537","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.02537","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02537","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,180],"development":[2],"of":[3,183],"large":[4],"language":[5],"models":[6],"(LLMs),":[7],"numerous":[8],"studies":[9],"integrate":[10],"LLMs":[11,41],"through":[12],"operator-like":[13],"components":[14,39],"to":[15,51,89,198,201,215],"enhance":[16],"relational":[17,45],"data":[18,228],"processing":[19],"tasks,":[20],"e.g.,":[21],"filters":[22],"with":[23,104,192],"semantic":[24,35,212],"predicates,":[25],"knowledge-augmented":[26],"table":[27],"imputation,":[28],"reasoning-driven":[29],"entity":[30],"matching":[31],"and":[32,72,93,101,107,121,138,145,171,224,229],"more":[33,129],"challenging":[34,147],"query":[36,152],"processing.":[37],"These":[38],"invoke":[40],"while":[42],"preserving":[43],"a":[44,85,114],"input/output":[46],"interface,":[47],"which":[48],"we":[49,82,111,157,219],"refer":[50],"as":[52],"LLM-Enhanced":[53],"Relational":[54],"Operators":[55],"(LROs).":[56],"From":[57],"an":[58,188,203],"operator":[59],"perspective,":[60],"unfortunately,":[61],"these":[62,193],"existing":[63,91,184],"LROs":[64,160],"suffer":[65],"from":[66],"fragmented":[67],"definition,":[68],"various":[69,162],"implementation":[70,108],"strategies":[71],"inadequate":[73],"evaluation":[74,230],"benchmarks.":[75],"To":[76],"this":[77,80],"end,":[78],"in":[79,141,196],"paper,":[81],"first":[83],"establish":[84],"unified":[86],"LRO":[87,168,189,205],"taxonomy":[88],"align":[90],"LROs,":[92],"categorize":[94],"them":[95],"into:":[96],"Select,":[97],"Match,":[98],"Impute,":[99],"Cluster":[100],"Order,":[102],"along":[103],"their":[105],"operands":[106],"variants.":[109],"Second,":[110],"design":[112,169,202],"LROBench,":[113],"comprehensive":[115],"benchmark":[116,227],"featuring":[117],"290":[118],"single-LRO":[119,143],"queries":[120,149],"60":[122],"multi-LRO":[123,148,185,208],"queries,":[124],"spanning":[125],"27":[126],"databases":[127],"across":[128],"than":[130],"10":[131],"domains.":[132],"LROBench":[133],"covers":[134],"all":[135,226],"operating":[136],"logics":[137],"operand":[139],"granularities":[140],"its":[142],"workload,":[144],"provides":[146],"stratified":[150],"by":[151],"complexity.":[153],"Based":[154],"on":[155],"these,":[156],"evaluate":[158],"individual":[159],"under":[161],"implementations,":[163],"deriving":[164],"practical":[165],"insights":[166],"into":[167],"choices":[170],"summarizing":[172],"our":[173],"empirical":[174],"best":[175,194],"practices.":[176],"We":[177],"further":[178],"compare":[179],"end-to-end":[181],"performance":[182],"systems":[186,209],"against":[187],"suite":[190],"instantiated":[191],"practices,":[195],"order":[197],"investigate":[199],"how":[200],"effective":[204],"set":[206],"for":[207],"targeting":[210],"complex":[211],"queries.":[213],"Last,":[214],"facilitate":[216],"future":[217,222],"work,":[218],"outline":[220],"promising":[221],"directions":[223],"open-source":[225],"code,":[231],"available":[232],"at":[233],"https://github.com/LROBench/LROBench/.":[234]},"counts_by_year":[],"updated_date":"2026-03-05T07:36:02.291473","created_date":"2026-03-05T00:00:00"}