{"id":"https://openalex.org/W7166834192","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1334","title":"RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models","display_name":"RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166834192","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1334"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1334","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1334","pdf_url":"https://aclanthology.org/2026.findings-acl.1334.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.1334.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015103614","display_name":"Arya Hadizadeh Moghaddam","orcid":"https://orcid.org/0000-0003-0935-4756"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arya Hadizadeh Moghaddam","raw_affiliation_strings":["University of Kansas , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Kansas , USA","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134181335","display_name":"Drew Ross","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Drew Ross","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092710033","display_name":"Mohsen Nayebi Kerdabadi","orcid":"https://orcid.org/0009-0007-5729-1565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohsen Nayebi Kerdabadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139751352","display_name":"Dongjie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongjie Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139792049","display_name":"Zijun Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijun Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.82399723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26766","last_page":"26778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.1177000030875206,"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":0.1177000030875206,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.09749999642372131,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.08649999648332596,"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/encoder","display_name":"Encoder","score":0.4781000018119812},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3926999866962433},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.30070000886917114},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.28360000252723694},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.2799000144004822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610000133514404},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4203999936580658},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38029998540878296},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1334","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1334","pdf_url":"https://aclanthology.org/2026.findings-acl.1334.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1334","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1334","pdf_url":"https://aclanthology.org/2026.findings-acl.1334.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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166834192.pdf","grobid_xml":"https://content.openalex.org/works/W7166834192.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"strong":[6],"promise":[7],"for":[8,27],"mining":[9],"Electronic":[10],"Health":[11],"Records":[12],"(EHRs)":[13],"by":[14],"reasoning":[15],"over":[16],"longitudinal":[17,63,129],"clinical":[18,162],"information":[19,134],"to":[20,58,127],"capture":[21,59],"contextrich":[22],"patient":[23,89],"trajectories.However,":[24],"leveraging":[25,94],"LLMs":[26,78],"structured":[28,109],"EHRs":[29],"(e.g.,":[30],"standardized":[31],"diagnosis":[32],"and":[33,52,62,131,148,157],"medication":[34],"codes)":[35],"presents":[36],"two":[37],"key":[38],"challenges.First,":[39],"translating":[40],"timestamped":[41],"EHR":[42,110,144],"sequences":[43],"into":[44],"plain":[45],"text":[46],"can":[47],"obscure":[48],"both":[49,155],"temporal":[50],"structure":[51],"code":[53,60],"identities,":[54],"weakening":[55],"the":[56],"ability":[57],"cooccurrence":[61],"regularities.Second,":[64],"unlike":[65],"cohort-trained":[66],"predictive":[67],"models":[68],"that":[69,107,151],"learn":[70],"a":[71,83,103,141],"shared,":[72],"task-aligned":[73,143],"representation":[74],"space":[75],"across":[76,160],"patients,":[77],"are":[79],"often":[80],"applied":[81],"in":[82],"case-isolated":[84],"inference":[85],"setting":[86],"where":[87],"each":[88],"is":[90],"processed":[91],"independently":[92],"without":[93,115],"population-level":[95,133],"patterns.To":[96],"address":[97],"these":[98],"challenges,":[99],"we":[100],"introduce":[101],"Re-PrompT,":[102],"time-aware":[104],"LLM":[105],"framework":[106],"integrates":[108],"encoders":[111],"through":[112,135],"prompt":[113,137],"tuning,":[114],"modifying":[116],"underlying":[117],"architectures.Specifically,":[118],"RePrompT":[119,152],"recurrently":[120],"incorporates":[121],"latent":[122],"states":[123],"from":[124,140],"prior":[125],"visits":[126],"preserve":[128],"information,":[130],"injects":[132],"trainable":[136],"tokens":[138],"derived":[139],"cohorttrained,":[142],"encoder.Experiments":[145],"on":[146],"MIMIC-III":[147],"MIMIC-IV":[149],"demonstrate":[150],"consistently":[153],"outperforms":[154],"EHR-based":[156],"LLM-based":[158],"baselines":[159],"multiple":[161],"prediction":[163],"tasks.":[164]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}