{"id":"https://openalex.org/W4415317452","doi":"https://doi.org/10.1109/fllm67465.2025.11391217","title":"Multi-Model Synthetic Training for Mission-Critical Small Language Models","display_name":"Multi-Model Synthetic Training for Mission-Critical Small Language Models","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W4415317452","doi":"https://doi.org/10.1109/fllm67465.2025.11391217"},"language":"en","primary_location":{"id":"doi:10.1109/fllm67465.2025.11391217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11391217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.13047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120050124","display_name":"Nolan Platt","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nolan Platt","raw_affiliation_strings":["Virginia Tech,Blacksburg,Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech,Blacksburg,Virginia","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":null,"display_name":"Pragyansmita Nayak","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Pragyansmita Nayak","raw_affiliation_strings":["Hitachi Vantara Federal,Reston,Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi Vantara Federal,Reston,Virginia","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23829744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"685","last_page":"692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.878600001335144,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.878600001335144,"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/overfitting","display_name":"Overfitting","score":0.777999997138977},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6302000284194946},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5964000225067139},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5918999910354614},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5310999751091003},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.4189999997615814},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.3847000002861023},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.34630000591278076}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.777999997138977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465999722480774},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6302000284194946},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5964000225067139},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5918999910354614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.54830002784729},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4781999886035919},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3249000012874603},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/fllm67465.2025.11391217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11391217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.13047","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.13047","pdf_url":"https://arxiv.org/pdf/2509.13047","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.13047","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.13047","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,"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.13047","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.13047","pdf_url":"https://arxiv.org/pdf/2509.13047","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415317452.pdf","grobid_xml":"https://content.openalex.org/works/W4415317452.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W4406266037","https://openalex.org/W4402671823","https://openalex.org/W2911489562","https://openalex.org/W4389519059","https://openalex.org/W4378714768","https://openalex.org/W4388979610","https://openalex.org/W4402670790","https://openalex.org/W4391929907","https://openalex.org/W4404200101","https://openalex.org/W4404783885","https://openalex.org/W4243639737","https://openalex.org/W4379536072"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"across":[8],"many":[9],"domains,":[10],"yet":[11],"their":[12],"application":[13],"to":[14,125,135],"specialized":[15,144,168],"fields":[16],"remains":[17],"constrained":[18],"by":[19,42],"the":[20,136,164],"scarcity":[21],"and":[22,71,78,82,147,182],"complexity":[23],"of":[24,139,167],"domain-specific":[25],"training":[26],"data.":[27],"We":[28,108],"present":[29],"a":[30,35,103,149],"novel":[31],"approach":[32,173],"that":[33,110,128],"achieves":[34,91],"261x":[36],"cost":[37],"reduction":[38],"for":[39,53,106,143,153],"maritime":[40,95,178],"intelligence":[41],"using":[43,50,102],"LLMs":[44],"as":[45],"one-time":[46],"teachers":[47],"rather":[48],"than":[49,101],"them":[51],"directly":[52],"inference.":[54,107],"Our":[55,132],"method":[56],"transforms":[57],"3.2":[58],"billion":[59],"Automatic":[60],"Identification":[61],"System":[62],"(AIS)":[63],"vessel":[64,183],"tracking":[65],"records":[66],"into":[67],"21,543":[68],"synthetic":[69,140],"question":[70],"answer":[72],"pairs":[73],"through":[74],"multi-model":[75],"generation":[76,142],"(GPT-4o":[77],"o3-mini),":[79],"preventing":[80],"overfitting":[81],"ensuring":[83],"accurate":[84],"reasoning.":[85],"The":[86],"resulting":[87],"fine-tuned":[88],"Qwen2.5-7B":[89],"model":[90,105],"75%":[92],"accuracy":[93,123],"on":[94],"tasks,":[96],"while":[97],"being":[98],"substantially":[99],"cheaper":[100,112],"larger":[104,126],"show":[109],"smaller,":[111],"models":[113,127],"-":[114,119],"when":[115],"fine":[116],"tuned":[117],"properly":[118],"can":[120],"provide":[121],"similar":[122],"compared":[124],"are":[129],"prohibitively":[130],"expensive.":[131],"work":[133],"contributes":[134],"growing":[137,165],"field":[138,166],"dataset":[141],"AI":[145],"applications":[146,176],"presents":[148],"highly":[150],"reproducible":[151],"framework":[152],"domains":[154],"where":[155],"manual":[156],"annotation":[157],"is":[158],"infeasible.":[159],"Beyond":[160],"expanding":[161],"research":[162],"in":[163,177,187],"small":[169],"language":[170],"models,":[171],"our":[172],"has":[174],"immediate":[175],"safety,":[179],"security":[180],"operations,":[181],"traffic":[184],"management":[185],"systems":[186],"various":[188],"industries.":[189]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-18T00:00:00"}