{"id":"https://openalex.org/W7131133956","doi":"https://doi.org/10.1145/3774816.3774838","title":"Semantic Encoding in Medical LLMs for Vocabulary Standardisation","display_name":"Semantic Encoding in Medical LLMs for Vocabulary Standardisation","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W7131133956","doi":"https://doi.org/10.1145/3774816.3774838"},"language":null,"primary_location":{"id":"doi:10.1145/3774816.3774838","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774816.3774838","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 18th Health Informatics Knowledge Management Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774816.3774838","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126612415","display_name":"Samuel Thomas Mainwood","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Samuel Thomas Mainwood","raw_affiliation_strings":["Data Science and AI(DSAI), School of Computing Technologies, RMIT University, Melbourne, Victoria, Australia"],"raw_orcid":"https://orcid.org/0009-0003-6919-1239","affiliations":[{"raw_affiliation_string":"Data Science and AI(DSAI), School of Computing Technologies, RMIT University, Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123507044","display_name":"Aashish Bhandari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Aashish Bhandari","raw_affiliation_strings":["Data Science and AI(DSAI), School of Computing Technologies, RMIT University, Melbourne, Victoria, Australia"],"raw_orcid":"https://orcid.org/0009-0000-1519-2736","affiliations":[{"raw_affiliation_string":"Data Science and AI(DSAI), School of Computing Technologies, RMIT University, Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124317568","display_name":"Sonika Tyagi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Sonika Tyagi","raw_affiliation_strings":["Data Science and AI(DSAI), School of Computing Technologies, RMIT University, Melbourne, Vic, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0181-6258","affiliations":[{"raw_affiliation_string":"Data Science and AI(DSAI), School of Computing Technologies, RMIT University, Melbourne, Vic, Australia","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69570212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3828999996185303,"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/T10028","display_name":"Topic Modeling","score":0.3828999996185303,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.24240000545978546,"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":0.16179999709129333,"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/vocabulary","display_name":"Vocabulary","score":0.7117000222206116},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6205000281333923},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5005999803543091},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46129998564720154},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4318999946117401},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4180999994277954},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4115000069141388},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4066999852657318}],"concepts":[{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7117000222206116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593999862670898},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6205000281333923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5552999973297119},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5392000079154968},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5005999803543091},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4180999994277954},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41029998660087585},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774816.3774838","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774816.3774838","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 18th Health Informatics Knowledge Management Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774816.3774838","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774816.3774838","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 18th Health Informatics Knowledge Management Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.616641104221344}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2068800403","https://openalex.org/W2107764756","https://openalex.org/W2159583324","https://openalex.org/W2778796877","https://openalex.org/W2890827016","https://openalex.org/W2911489562","https://openalex.org/W2998702515","https://openalex.org/W3158665049","https://openalex.org/W3172427031","https://openalex.org/W4206629261","https://openalex.org/W4214584464","https://openalex.org/W4304991627","https://openalex.org/W4383605193","https://openalex.org/W4385573637","https://openalex.org/W4387537475","https://openalex.org/W4388514671","https://openalex.org/W4392223100","https://openalex.org/W4402387323","https://openalex.org/W4404062849","https://openalex.org/W4406741160"],"related_works":[],"abstract_inverted_index":{"High-quality,":[0],"standardised":[1],"medical":[2],"data":[3],"availability":[4],"remains":[5],"a":[6],"bottleneck":[7],"for":[8,28,48,150],"digital":[9],"health":[10],"and":[11,30,56,77,106,116,119,145],"AI":[12],"model":[13,117],"development.":[14],"A":[15],"major":[16],"hurdle":[17],"is":[18,111],"translating":[19],"noisy":[20],"free":[21],"text":[22],"into":[23],"controlled":[24],"clinical":[25,147],"vocabularies,":[26],"aiming":[27],"harmonisation":[29],"interoperability,":[31],"especially":[32],"when":[33],"source":[34],"datasets":[35],"are":[36,126,133],"inconsistent":[37],"or":[38],"incomplete.":[39],"We":[40,61,70],"benchmark":[41],"domain-specific":[42],"encoder":[43],"models":[44,81,95,99,132],"against":[45],"general":[46,98],"LLMs":[47,141],"semantic-embedding":[49],"retrieval":[50,105],"using":[51],"minimal":[52],"vocabulary":[53,152],"building":[54],"blocks":[55],"test":[57],"several":[58],"prompt":[59,64,92,114],"techniques.":[60],"also":[62],"try":[63],"augmentation":[65],"with":[66],"LLM-generated":[67,124],"differential":[68],"definitions.":[69],"tested":[71],"these":[72],"prompts":[73],"on":[74],"open-source":[75,139],"Llama":[76,80],"medically":[78],"fine-tuned":[79],"to":[82,113],"steer":[83],"their":[84],"alignment":[85],"toward":[86],"accurate":[87],"concept":[88],"assignment":[89],"across":[90],"multiple":[91],"formats.":[93],"Domain-tuned":[94],"consistently":[96],"outperform":[97],"of":[100,122],"the":[101,120,135,143],"same":[102],"size":[103],"in":[104],"generative":[107,140],"tasks.":[108],"However,":[109],"performance":[110],"sensitive":[112],"design":[115],"size,":[118],"benefits":[121],"adding":[123],"context":[125],"inconsistent.":[127],"While":[128],"newer,":[129],"larger":[130],"foundation":[131],"closing":[134],"gap,":[136],"today\u2019s":[137],"lightweight":[138],"lack":[142],"stability":[144],"embedded":[146],"knowledge":[148],"needed":[149],"deterministic":[151],"standardisation.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-24T00:00:00"}