{"id":"https://openalex.org/W7225201617","doi":"https://doi.org/10.48550/arxiv.2611.02373","title":"Mixed-Type Relational Database Synthesis with Graph-Prompted Language Model","display_name":"Mixed-Type Relational Database Synthesis with Graph-Prompted Language Model","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225201617","doi":"https://doi.org/10.48550/arxiv.2611.02373"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02373","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02373","pdf_url":"https://arxiv.org/pdf/2611.02373","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.02373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160527119","display_name":"Yuxiang Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yuxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140825260","display_name":"Mengshi Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Mengshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160532927","display_name":"Jianwei Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jianwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160415833","display_name":"Wenjie Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160492202","display_name":"Kai Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.3400999903678894,"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":0.3400999903678894,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.3181000053882599,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.13670000433921814,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/heterogeneous-graphs","display_name":"heterogeneous graphs","score":0.6539999842643738},{"id":"https://openalex.org/keywords/small-language-models","display_name":"small language models","score":0.7710000276565552},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9860000014305115},{"id":"https://openalex.org/keywords/attribute-dependencies","display_name":"attribute dependencies","score":0.49300000071525574},{"id":"https://openalex.org/keywords/semantic-consistency","display_name":"semantic consistency","score":0.8190000057220459},{"id":"https://openalex.org/keywords/data-privacy","display_name":"data privacy","score":0.3709999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363000154495239},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.7520999908447266},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.5953999757766724},{"id":"https://openalex.org/C5968703","wikidata":"https://www.wikidata.org/wiki/Q267136","display_name":"Database model","level":3,"score":0.5375000238418579},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C103593891","wikidata":"https://www.wikidata.org/wiki/Q624546","display_name":"Entity\u2013relationship model","level":3,"score":0.4700999855995178},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4237000048160553},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.37130001187324524},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36730000376701355},{"id":"https://openalex.org/C24394798","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database management system","level":3,"score":0.3312999904155731},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33070001006126404},{"id":"https://openalex.org/C99436015","wikidata":"https://www.wikidata.org/wiki/Q1722436","display_name":"Relational calculus","level":4,"score":0.3280999958515167},{"id":"https://openalex.org/C12439846","wikidata":"https://www.wikidata.org/wiki/Q4809258","display_name":"Database theory","level":3,"score":0.3224000036716461},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32199999690055847},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C65647387","wikidata":"https://www.wikidata.org/wiki/Q1781706","display_name":"Conjunctive query","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2879999876022339},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C55596503","wikidata":"https://www.wikidata.org/wiki/Q1431648","display_name":"Data definition language","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.02373","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02373","pdf_url":"https://arxiv.org/pdf/2611.02373","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.02373","doi":"https://doi.org/10.48550/arxiv.2611.02373","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02373","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.02373","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02373","pdf_url":"https://arxiv.org/pdf/2611.02373","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414891826","https://openalex.org/W7112919255","https://openalex.org/W7138470191","https://openalex.org/W4416035378","https://openalex.org/W7172019040","https://openalex.org/W7056830788","https://openalex.org/W4416452019","https://openalex.org/W4402004019","https://openalex.org/W4413772207","https://openalex.org/W7208813213"],"abstract_inverted_index":{"Data":[0],"access":[1],"is":[2],"often":[3],"limited":[4],"by":[5,145],"privacy":[6],"or":[7],"proprietary":[8],"restrictions,":[9],"motivating":[10],"relational":[11,50,104,186],"database":[12,51,91],"synthesis,":[13],"which":[14],"synthesizes":[15],"realistic":[16,36,49],"contents":[17],"across":[18,85],"related":[19],"tables.":[20],"Relational":[21],"databases":[22,187],"couple":[23],"multi-table":[24],"structure":[25],"with":[26,53,141,159,197],"mixed-type":[27,54,99],"attributes":[28],"and":[29,63,75,84,102,123,170,201],"intricate":[30],"semantic":[31,132,151,199],"dependencies":[32,82,173],"among":[33],"values,":[34],"making":[35],"synthesis":[37,52],"challenging.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"REMIX,":[44],"a":[45,58,64,160],"unified":[46],"framework":[47],"for":[48,114],"attributes.":[55],"REMIX":[56,192],"integrates":[57],"small":[59],"language":[60,66],"model":[61,67],"(SLM)":[62],"large":[65],"(LLM)":[68],"through":[69,125,156],"two":[70],"key":[71],"phases:":[72],"Graph-to-Prompt":[73,87],"Tuning":[74,88],"Collaborative":[76,134],"SLM-LLM":[77,135],"Decoding.":[78],"To":[79],"capture":[80],"attribute":[81,127],"within":[83],"tables,":[86],"represents":[89],"the":[90,120,164,189],"as":[92,111],"an":[93,115,146],"attributed":[94],"heterogeneous":[95],"graph.":[96],"We":[97,117],"project":[98],"record":[100,139],"embeddings":[101],"aggregated":[103],"context":[105],"into":[106,174],"soft":[107],"prompts":[108],"that":[109,177],"serve":[110],"continuous":[112],"vectors":[113],"SLM.":[116],"jointly":[118],"optimize":[119],"graph-to-prompt":[121],"mapping":[122],"SLM":[124],"autoregressive":[126],"reconstruction.":[128],"Furthermore,":[129],"to":[130],"reduce":[131],"inconsistencies,":[133],"Decoding":[136],"combines":[137],"SLM-based":[138],"generation":[140],"repair":[142,178],"programs":[143,176],"induced":[144],"LLM.":[147],"The":[148],"LLM":[149],"discovers":[150],"dependencies,":[152],"iteratively":[153],"refines":[154],"them":[155],"independent":[157],"validation":[158],"statistical":[161],"bound":[162],"on":[163,183],"overall":[165],"probability":[166],"of":[167,191],"false":[168],"acceptance,":[169],"translates":[171],"validated":[172],"tested":[175],"generated":[179],"values.":[180],"Extensive":[181],"experiments":[182],"seven":[184],"real-world":[185],"demonstrate":[188],"effectiveness":[190],"in":[193],"generating":[194],"high-fidelity":[195],"data":[196],"improved":[198],"consistency":[200],"downstream":[202],"utility.":[203]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}