{"id":"https://openalex.org/W7160958323","doi":"https://doi.org/10.48550/arxiv.2605.09855","title":"Concordia: Self-Improving Synthetic Tables for Federated LLMs","display_name":"Concordia: Self-Improving Synthetic Tables for Federated LLMs","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160958323","doi":"https://doi.org/10.48550/arxiv.2605.09855"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.09855","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09855","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":null,"license_id":null,"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.2605.09855","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135991974","display_name":"Jimin Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jimin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135981032","display_name":"Duanyu Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Duanyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135926452","display_name":"Nuo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Nuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136000632","display_name":"Xiaoyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135993145","display_name":"Zhiqiang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhiqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135926122","display_name":"Xueqing Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Xueqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135931122","display_name":"Mingquan Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Mingquan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135924372","display_name":"Prayag Tiwari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiwari, Prayag","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135947675","display_name":"Guojun Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Guojun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135996431","display_name":"Alejandro Lopez-Lira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lopez-Lira, Alejandro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135981178","display_name":"Sophia Ananiadou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ananiadou, Sophia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7232999801635742,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7232999801635742,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.04960000142455101,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.024000000208616257,"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/raw-data","display_name":"Raw data","score":0.6355999708175659},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5956000089645386},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5719000101089478},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4564000070095062},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3589000105857849},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.3580999970436096},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.35429999232292175},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.33570000529289246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7529000043869019},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.6355999708175659},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5956000089645386},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.3580999970436096},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.33570000529289246},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3009999990463257},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2567000091075897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C2780866740","wikidata":"https://www.wikidata.org/wiki/Q5227345","display_name":"Data retention","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.09855","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09855","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.09855","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09855","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1],"(FL)":[2],"enables":[3],"training":[4,82,118],"large":[5],"language":[6],"models":[7,112],"(LLMs)":[8],"without":[9,166],"sharing":[10],"raw":[11,72],"data,":[12],"but":[13],"adapting":[14],"LLMs":[15,67],"under":[16,59],"strict":[17],"data":[18,29,76,99],"isolation":[19],"and":[20,74,80,181,192,200],"non-IID":[21],"client":[22,110,144],"distributions":[23],"remains":[24],"challenging":[25],"in":[26],"practice.":[27],"Synthetic":[28],"offers":[30],"a":[31,92],"natural":[32],"privacy-preserving":[33],"surrogate":[34],"for":[35],"local":[36,81,137],"training,":[37],"yet":[38],"existing":[39],"federated":[40,64,102,188],"pipelines":[41],"typically":[42],"treat":[43],"synthetic":[44,87,98,120,134,148],"generation":[45,100],"as":[46],"static":[47,199],"or":[48,170],"loosely":[49],"coupled":[50],"with":[51,101],"downstream":[52],"optimization,":[53],"leading":[54],"to":[55,132,194,198],"rapidly":[56],"diminishing":[57],"utility":[58,104,126],"heterogeneous":[60,161],"clients.":[61],"We":[62,89],"study":[63],"adaptation":[65],"of":[66,160],"on":[68,86,119,175],"tabular":[69,177],"tasks":[70],"where":[71],"records":[73],"validation":[75,103,130,172],"cannot":[77],"be":[78],"shared,":[79],"must":[83],"rely":[84],"entirely":[85],"tables.":[88,121],"propose":[90],"Concordia,":[91],"tri-level":[93],"optimization":[94,154],"framework":[95],"that":[96,184],"aligns":[97],"despite":[105],"these":[106],"constraints.":[107],"At":[108,139],"the":[109,140],"level,":[111,142],"are":[113],"adapted":[114],"via":[115],"parameter-efficient":[116],"LoRA":[117],"Clients":[122],"additionally":[123],"learn":[124],"lightweight":[125],"scorers":[127,162],"from":[128,179],"private":[129],"feedback":[131],"reweight":[133],"samples":[135],"during":[136],"training.":[138],"outer":[141],"each":[143],"refines":[145],"its":[146],"own":[147],"table":[149],"generator":[150,168],"using":[151],"group-relative":[152],"policy":[153],"(GRPO),":[155],"guided":[156],"by":[157],"an":[158],"ensemble":[159],"shared":[163],"across":[164],"clients,":[165],"aggregating":[167],"parameters":[169],"exposing":[171],"data.":[173],"Experiments":[174],"privacy-sensitive":[176],"benchmarks":[178],"finance":[180],"healthcare":[182],"demonstrate":[183],"Concordia":[185],"consistently":[186],"improves":[187],"performance,":[189],"cross-client":[190],"stability,":[191],"robustness":[193],"distribution":[195],"shift":[196],"compared":[197],"decoupled":[201],"synthetic-data":[202],"baselines.":[203]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-13T00:00:00"}