{"id":"https://openalex.org/W4414261039","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1405","title":"DualAlign: Generating Clinically Grounded Synthetic Data","display_name":"DualAlign: Generating Clinically Grounded Synthetic Data","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414261039","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1405"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1405","pdf_url":"https://aclanthology.org/2026.findings-acl.1405.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1405.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100448493","display_name":"Rui Li","orcid":"https://orcid.org/0000-0002-5161-2109"},"institutions":[{"id":"https://openalex.org/I4210095851","display_name":"VA New England Healthcare System","ror":"https://ror.org/00s61s029","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210095851"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rumeng Li","raw_affiliation_strings":["Umass Amherst, VA Bedford Healthcare System"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Umass Amherst, VA Bedford Healthcare System","institution_ids":["https://openalex.org/I4210095851"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107954382","display_name":"Xun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xun Wang","raw_affiliation_strings":["Micrsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Micrsoft","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017601806","display_name":"Hong Yu","orcid":"https://orcid.org/0000-0001-9263-5035"},"institutions":[{"id":"https://openalex.org/I1303243448","display_name":"UMass Memorial Health Care","ror":"https://ror.org/00pq96s96","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1303243448"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Yu","raw_affiliation_strings":["Umass Lowell, Umass Amherst, VA Bedford Healthcare System"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Umass Lowell, Umass Amherst, VA Bedford Healthcare System","institution_ids":["https://openalex.org/I1303243448"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.00606447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28189","last_page":"28208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.7847999930381775,"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":0.7847999930381775,"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":0.6675999760627747,"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/synthetic-data","display_name":"Synthetic data","score":0.6265000104904175},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4952000081539154},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.47029998898506165},{"id":"https://openalex.org/keywords/observational-study","display_name":"Observational study","score":0.45829999446868896},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38839998841285706},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.3855000138282776},{"id":"https://openalex.org/keywords/demographics","display_name":"Demographics","score":0.31679999828338623},{"id":"https://openalex.org/keywords/clinical-trial","display_name":"Clinical trial","score":0.3149000108242035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6736999750137329},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6265000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016999840736389},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4629000127315521},{"id":"https://openalex.org/C23131810","wikidata":"https://www.wikidata.org/wiki/Q818574","display_name":"Observational study","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4140999913215637},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3855000138282776},{"id":"https://openalex.org/C2780084366","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demographics","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C535046627","wikidata":"https://www.wikidata.org/wiki/Q30612","display_name":"Clinical trial","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C3020672099","wikidata":"https://www.wikidata.org/wiki/Q857354","display_name":"Longitudinal data","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28529998660087585},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1405","pdf_url":"https://aclanthology.org/2026.findings-acl.1405.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"doi:10.1101/2025.09.09.25335422","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.09.09.25335422","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2025/09/12/2025.09.09.25335422.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1405","pdf_url":"https://aclanthology.org/2026.findings-acl.1405.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414261039.pdf","grobid_xml":"https://content.openalex.org/works/W4414261039.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W3012501605","https://openalex.org/W3088033826","https://openalex.org/W3125656453","https://openalex.org/W3161306590","https://openalex.org/W3166254754","https://openalex.org/W3178287460","https://openalex.org/W3214401235","https://openalex.org/W4200264568","https://openalex.org/W4224022798","https://openalex.org/W4288428515","https://openalex.org/W4308292299","https://openalex.org/W4313644512","https://openalex.org/W4321595817","https://openalex.org/W4324309277","https://openalex.org/W4377019940","https://openalex.org/W4387457231","https://openalex.org/W4388725043","https://openalex.org/W4389520213","https://openalex.org/W4401542967","https://openalex.org/W4403789625","https://openalex.org/W4405492391","https://openalex.org/W4405865167","https://openalex.org/W4406944279","https://openalex.org/W4407174976","https://openalex.org/W4409737503","https://openalex.org/W4410090070","https://openalex.org/W4410302384","https://openalex.org/W4410415527"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Synthetic":[1],"clinical":[2,39,63,110,163],"data":[3,43,124,134,159],"are":[4],"increasingly":[5],"important":[6],"for":[7,153],"advancing":[8],"AI":[9],"in":[10,28],"healthcare,":[11],"given":[12],"strict":[13],"privacy":[14],"constraints":[15],"on":[16,74,132],"real-world":[17,86,109],"EHRs,":[18],"limited":[19],"availability":[20],"of":[21,120],"annotated":[22],"rare-condition":[23],"data,":[24],"and":[25,48,62,77,80,122],"systemic":[26],"biases":[27],"observational":[29],"datasets.":[30],"While":[31,140],"large":[32],"language":[33],"models":[34,130],"(LLMs)":[35],"can":[36],"generate":[37],"fluent":[38],"text,":[40],"producing":[41],"synthetic":[42,138,158],"that":[44,58,106],"is":[45],"both":[46],"realistic":[47],"clinically":[49,155],"meaningful":[50],"remains":[51],"challenging.":[52],"We":[53],"introduce":[54],"DualAlign,":[55],"a":[56,98,118,150],"framework":[57],"enhances":[59],"statistical":[60,69],"fidelity":[61],"plausibility":[64],"through":[65],"dual":[66],"alignment:":[67],"(1)":[68],"alignment,":[70,83],"which":[71,84],"conditions":[72],"generation":[73],"patient":[75],"demographics":[76],"risk":[78],"factors;":[79],"(2)":[81],"semantic":[82],"incorporates":[85],"symptom":[87],"trajectories":[88],"to":[89,160],"guide":[90],"content":[91],"generation.":[92],"Using":[93],"Alzheimer\u2019s":[94],"disease":[95],"(AD)":[96],"as":[97],"case":[99],"study,":[100],"DualAlign":[101,141],"produces":[102],"context-grounded":[103],"symptom-level":[104],"sentences":[105],"better":[107],"reflect":[108],"documentation.":[111],"Fine-tuning":[112],"an":[113],"LLaMA":[114],"3.1\u20138B":[115],"model":[116],"with":[117],"combination":[119],"DualAlign-generated":[121],"human-annotated":[123],"yields":[125],"sub-stantial":[126],"performance":[127],"gains":[128],"over":[129],"trained":[131],"gold":[133],"alone":[135],"or":[136],"unguided":[137],"baselines.":[139],"does":[142],"not":[143],"fully":[144],"capture":[145],"longitudinal":[146],"complexity,":[147],"it":[148],"offers":[149],"practical":[151],"approach":[152],"generating":[154],"grounded,":[156],"privacy-preserving":[157],"support":[161],"low-resource":[162],"text":[164],"analysis.":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}