{"id":"https://openalex.org/W7147057239","doi":"https://doi.org/10.48550/arxiv.2603.27254","title":"Amalgam: Hybrid LLM-PGM Synthesis Algorithm for Accuracy and Realism","display_name":"Amalgam: Hybrid LLM-PGM Synthesis Algorithm for Accuracy and Realism","publication_year":2026,"publication_date":"2026-03-28","ids":{"openalex":"https://openalex.org/W7147057239","doi":"https://doi.org/10.48550/arxiv.2603.27254"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2603.27254","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.27254","pdf_url":"https://arxiv.org/pdf/2603.27254","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.27254","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115904565","display_name":"Antheas Kapenekakis","orcid":"https://orcid.org/0000-0003-0924-7811","observed_orcids":["https://orcid.org/0000-0003-0924-7811"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kapenekakis, Antheas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055390209","display_name":"Bent Thomsen","orcid":"https://orcid.org/0000-0002-5853-7973","observed_orcids":["https://orcid.org/0000-0002-5853-7973"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomsen, Bent","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132642646","display_name":"Katja Hose","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hose, Katja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001455999","display_name":"Michele Albano","orcid":"https://orcid.org/0000-0002-3777-9981","observed_orcids":["https://orcid.org/0000-0002-3777-9981"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Albano, Michele","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":true,"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":0.9115999937057495,"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":0.9115999937057495,"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/T14509","display_name":"demographic modeling and climate adaptation","score":0.00860000029206276,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.006000000052154064,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/synthetic-data-generation","display_name":"synthetic data generation","score":0.9800000190734863},{"id":"https://openalex.org/keywords/probabilistic-graphical-models","display_name":"probabilistic graphical models","score":0.8690000176429749},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9700000286102295},{"id":"https://openalex.org/keywords/data-privacy","display_name":"data privacy","score":0.6259999871253967},{"id":"https://openalex.org/keywords/health-data","display_name":"health data","score":0.5329999923706055},{"id":"https://openalex.org/keywords/advanced-analytics","display_name":"advanced analytics","score":0.5239999890327454},{"id":"https://openalex.org/keywords/schema-complexity","display_name":"schema complexity","score":0.3790000081062317},{"id":"https://openalex.org/keywords/skewness","display_name":"skewness","score":0.42399999499320984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131999731063843},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6064000129699707},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5483999848365784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48649999499320984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46889999508857727},{"id":"https://openalex.org/C543847140","wikidata":"https://www.wikidata.org/wiki/Q2642826","display_name":"Realism","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40639999508857727},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2984927552","wikidata":"https://www.wikidata.org/wiki/Q845734","display_name":"Graphical display","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C62469222","wikidata":"https://www.wikidata.org/wiki/Q17092103","display_name":"Hybrid algorithm (constraint satisfaction)","level":5,"score":0.25540000200271606}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2603.27254","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.27254","pdf_url":"https://arxiv.org/pdf/2603.27254","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.2603.27254","doi":"https://doi.org/10.48550/arxiv.2603.27254","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27254","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:2603.27254","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.27254","pdf_url":"https://arxiv.org/pdf/2603.27254","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":[{"id":"https://openalex.org/F4320310490","display_name":"Villum Fonden","ror":"https://ror.org/007ww2d15"},{"id":"https://openalex.org/F4320313796","display_name":"Innovationsfonden","ror":"https://ror.org/00daj4111"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7147057239.pdf","grobid_xml":"https://content.openalex.org/works/W7147057239.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2980282514","https://openalex.org/W4385014449","https://openalex.org/W4404354513","https://openalex.org/W4405903187","https://openalex.org/W4412888764","https://openalex.org/W4414687920","https://openalex.org/W4414939355","https://openalex.org/W6947991961","https://openalex.org/W7075994024"],"related_works":["https://openalex.org/W7166886659","https://openalex.org/W7204961128","https://openalex.org/W7081064249","https://openalex.org/W4410409887","https://openalex.org/W7164752209","https://openalex.org/W4399794317","https://openalex.org/W7161684727","https://openalex.org/W7161553856","https://openalex.org/W7134922136","https://openalex.org/W7164183262"],"abstract_inverted_index":{"To":[0],"generate":[1],"synthetic":[2,32],"datasets,":[3],"e.g.,":[4],"in":[5],"domains":[6],"such":[7,26],"as":[8,27],"healthcare,":[9],"the":[10,51],"literature":[11],"proposes":[12],"approaches":[13],"of":[14],"two":[15],"main":[16],"types:":[17],"Probabilistic":[18],"Graphical":[19],"Models":[20],"(PGMs)":[21],"and":[22,47,87,105,118],"Deep":[23],"Learning":[24],"models,":[25],"LLMs.":[28],"While":[29],"PGMs":[30],"produce":[31,58],"data":[33,79,96,120],"that":[34,93],"can":[35],"be":[36],"used":[37],"for":[38,66,108],"advanced":[39,67,84],"analytics,":[40,85],"they":[41],"do":[42],"not":[43],"support":[44,54],"complex":[45,55],"schemas":[46,56],"datasets.":[48],"LLMs":[49],"on":[50],"other":[52],"hand,":[53],"but":[57],"skewed":[59],"dataset":[60],"distributions,":[61],"which":[62],"are":[63],"less":[64],"useful":[65],"analytics.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"therefore":[73],"present":[74],"Amalgam,":[75],"a":[76],"hybrid":[77],"LLM-PGM":[78],"synthesis":[80],"algorithm":[81],"supporting":[82],"both":[83],"realism,":[86],"tangible":[88],"privacy":[89],"properties.":[90],"We":[91],"show":[92],"Amalgam":[94],"synthesizes":[95],"with":[97],"an":[98],"average":[99],"91":[100],"%":[101],"$\u03c7^2":[102],"P$":[103],"value":[104],"scores":[106],"3.8/5":[107],"realism":[109],"using":[110],"our":[111],"proposed":[112],"metric,":[113],"where":[114],"state-of-the-art":[115],"is":[116,121],"3.3":[117],"real":[119],"4.7.":[122]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-04-02T00:00:00"}