{"id":"https://openalex.org/W7156304717","doi":"https://doi.org/10.48550/arxiv.2604.22061","title":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","display_name":"Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7156304717","doi":"https://doi.org/10.48550/arxiv.2604.22061"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.22061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22061","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.22061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134686790","display_name":"Xiaodi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaodi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134667263","display_name":"Yang Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121341194","display_name":"MunHwan Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Munhwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023803145","display_name":"Konstantinos Leventakos","orcid":"https://orcid.org/0000-0001-9784-8603"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leventakos, Konstantinos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134685705","display_name":"Young J. Juhn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juhn, Young J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134693888","display_name":"David Jones","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jones, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032470889","display_name":"Terence T. Sio","orcid":"https://orcid.org/0000-0003-4210-5479"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sio, Terence T.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663400","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-1103-7699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134709655","display_name":"Maria Vassilaki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vassilaki, Maria","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019653651","display_name":"Nansu Zong","orcid":"https://orcid.org/0000-0003-0066-9524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zong, Nansu","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/T13702","display_name":"Machine Learning in Healthcare","score":0.9501000046730042,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9501000046730042,"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/T10028","display_name":"Topic Modeling","score":0.0333000011742115,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.002300000051036477,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7781999707221985},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6947000026702881},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6366000175476074},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5891000032424927},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.5174999833106995},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5069000124931335},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.45089998841285706},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4318000078201294},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.4185999929904938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256999850273132},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7781999707221985},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6947000026702881},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6366000175476074},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5069000124931335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4887999892234802},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4641999900341034},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4318000078201294},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.4185999929904938},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3749000132083893},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.22061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22061","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.22061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22061","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":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4992442727088928,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Patient-trial":[0],"matching":[1],"requires":[2],"reasoning":[3],"over":[4],"long,":[5],"heterogeneous":[6],"electronic":[7],"health":[8],"records":[9],"(EHRs)":[10],"and":[11,21,65,118,125,142],"complex":[12],"eligibility":[13],"criteria,":[14],"posing":[15],"significant":[16],"challenges":[17],"for":[18,70,175,183],"scalability,":[19],"generalization,":[20],"computational":[22,159,203],"efficiency.":[23],"Existing":[24],"approaches":[25,199],"either":[26],"rely":[27],"on":[28,134],"full-document":[29],"processing":[30],"with":[31,200],"large":[32,66,97],"language":[33,67,98],"models":[34,99],"(LLMs),":[35],"which":[36],"is":[37,83,181],"computationally":[38],"expensive,":[39],"or":[40],"use":[41],"traditional":[42],"machine":[43],"learning":[44],"methods":[45],"that":[46,61,153,169],"struggle":[47],"to":[48,85,102,196],"capture":[49],"unstructured":[50,185],"clinical":[51,177,186],"narratives.":[52,187],"In":[53],"this":[54],"work,":[55],"we":[56],"propose":[57],"a":[58,143],"lightweight":[59,121,191],"framework":[60,75],"combines":[62],"retrieval-augmented":[63,81],"generation":[64,82],"model-based":[68],"modeling":[69,184],"scalable":[71,126],"patient-trial":[72],"matching.":[73],"The":[74],"explicitly":[76],"separates":[77],"two":[78],"key":[79],"components:":[80],"used":[84,101],"identify":[86],"clinically":[87,163],"relevant":[88],"segments":[89,106],"from":[90,147],"long":[91],"EHRs,":[92],"reducing":[93],"input":[94],"complexity,":[95],"while":[96,161],"are":[100,112],"encode":[103],"these":[104],"selected":[105],"into":[107],"informative":[108],"representations.":[109],"These":[110],"representations":[111,174],"further":[113,167],"refined":[114],"through":[115],"dimensionality":[116],"reduction":[117],"modeled":[119],"using":[120],"predictors,":[122],"enabling":[123],"efficient":[124],"downstream":[127],"classification.":[128],"We":[129,166],"evaluate":[130],"the":[131,189],"proposed":[132,190],"approach":[133],"multiple":[135],"public":[136],"benchmarks":[137],"(n2c2,":[138],"SIGIR,":[139],"TREC":[140],"2021/2022)":[141],"real-world":[144],"multimodal":[145],"dataset":[146],"Mayo":[148],"Clinic":[149],"(MCPMD).":[150],"Results":[151],"show":[152],"retrieval-based":[154],"information":[155],"selection":[156],"significantly":[157],"reduces":[158],"burden":[160],"preserving":[162],"meaningful":[164],"signals.":[165],"demonstrate":[168],"frozen":[170],"LLMs":[171],"provide":[172],"strong":[173],"structured":[176],"data,":[178],"whereas":[179],"fine-tuning":[180],"essential":[182],"Importantly,":[188],"pipeline":[192],"achieves":[193],"performance":[194],"comparable":[195],"end-to-end":[197],"LLM":[198],"substantially":[201],"lower":[202],"cost.":[204]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-28T00:00:00"}