{"id":"https://openalex.org/W4414648434","doi":"https://doi.org/10.1109/cibcb66090.2025.11177118","title":"Balanced Benchmarking of Zero-Shot and RAG Approaches for Biomedical Term Normalization","display_name":"Balanced Benchmarking of Zero-Shot and RAG Approaches for Biomedical Term Normalization","publication_year":2025,"publication_date":"2025-08-20","ids":{"openalex":"https://openalex.org/W4414648434","doi":"https://doi.org/10.1109/cibcb66090.2025.11177118"},"language":"en","primary_location":{"id":"doi:10.1109/cibcb66090.2025.11177118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb66090.2025.11177118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113004855","display_name":"Thanh Son","orcid":null},"institutions":[{"id":"https://openalex.org/I119942284","display_name":"Missouri State University","ror":"https://ror.org/01d2sez20","country_code":"US","type":"education","lineage":["https://openalex.org/I119942284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thanh Son Do","raw_affiliation_strings":["Missouri State University,Computer Science Department,Springfield,MO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri State University,Computer Science Department,Springfield,MO","institution_ids":["https://openalex.org/I119942284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046843425","display_name":"Daniel B. Hier","orcid":"https://orcid.org/0000-0002-6179-0793"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel B. Hier","raw_affiliation_strings":["Missouri University of Science & Technology,Kummer Institute Center for AI and AS,Rolla,MO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri University of Science & Technology,Kummer Institute Center for AI and AS,Rolla,MO","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040578359","display_name":"Tayo Obafemi-Ajayi","orcid":"https://orcid.org/0000-0002-0155-9733"},"institutions":[{"id":"https://openalex.org/I119942284","display_name":"Missouri State University","ror":"https://ror.org/01d2sez20","country_code":"US","type":"education","lineage":["https://openalex.org/I119942284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tayo Obafemi-Ajayi","raw_affiliation_strings":["Missouri State University,Cooperative Engineering Program,Springfield,MO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri State University,Cooperative Engineering Program,Springfield,MO","institution_ids":["https://openalex.org/I119942284"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35241701,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.8183000087738037,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.8183000087738037,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10977","display_name":"Optical Imaging and Spectroscopy Techniques","score":0.8167999982833862,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12994","display_name":"Infrared Thermography in Medicine","score":0.7628999948501587,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/ontology","display_name":"Ontology","score":0.7117000222206116},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6622999906539917},{"id":"https://openalex.org/keywords/open-biomedical-ontologies","display_name":"Open Biomedical Ontologies","score":0.5636000037193298},{"id":"https://openalex.org/keywords/snomed-ct","display_name":"SNOMED CT","score":0.5296000242233276},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.5142999887466431},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5081999897956848},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.44699999690055847},{"id":"https://openalex.org/keywords/semantic-integration","display_name":"Semantic integration","score":0.39649999141693115},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.3824000060558319}],"concepts":[{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7117000222206116},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6622999906539917},{"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/C137982476","wikidata":"https://www.wikidata.org/wiki/Q7072326","display_name":"Open Biomedical Ontologies","level":5,"score":0.5636000037193298},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.5296000242233276},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.44699999690055847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4424999952316284},{"id":"https://openalex.org/C110903229","wikidata":"https://www.wikidata.org/wiki/Q7449064","display_name":"Semantic integration","level":4,"score":0.39649999141693115},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.365200012922287},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35899999737739563},{"id":"https://openalex.org/C22550185","wikidata":"https://www.wikidata.org/wiki/Q7095047","display_name":"Ontology-based data integration","level":3,"score":0.3560999929904938},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3553999960422516},{"id":"https://openalex.org/C44681071","wikidata":"https://www.wikidata.org/wiki/Q4048820","display_name":"Systematized Nomenclature of Medicine","level":4,"score":0.35199999809265137},{"id":"https://openalex.org/C78726541","wikidata":"https://www.wikidata.org/wiki/Q3882785","display_name":"Upper ontology","level":3,"score":0.3467000126838684},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.3352999985218048},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C192800085","wikidata":"https://www.wikidata.org/wiki/Q5258530","display_name":"Semantic interoperability","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C2987395477","wikidata":"https://www.wikidata.org/wiki/Q135085","display_name":"Gene ontology","level":4,"score":0.2680000066757202},{"id":"https://openalex.org/C137003198","wikidata":"https://www.wikidata.org/wiki/Q7247296","display_name":"Process ontology","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C50971890","wikidata":"https://www.wikidata.org/wiki/Q7635093","display_name":"Suggested Upper Merged Ontology","level":4,"score":0.25290000438690186},{"id":"https://openalex.org/C98893333","wikidata":"https://www.wikidata.org/wiki/Q4339878","display_name":"Ontology alignment","level":4,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cibcb66090.2025.11177118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb66090.2025.11177118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"},{"id":"pmh:oai:bearworks.missouristate.edu:articles00-1252","is_oa":false,"landing_page_url":"https://bearworks.missouristate.edu/articles00/253","pdf_url":null,"source":{"id":"https://openalex.org/S4377196450","display_name":"BearWorks (Missouri State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119942284","host_organization_name":"Missouri State University","host_organization_lineage":["https://openalex.org/I119942284"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Scholarship","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2911489562","https://openalex.org/W3112600195","https://openalex.org/W4366219700","https://openalex.org/W4385848332","https://openalex.org/W4388616071","https://openalex.org/W4389538461","https://openalex.org/W4391387740","https://openalex.org/W4394782455","https://openalex.org/W4395067526","https://openalex.org/W4399280731","https://openalex.org/W4402683886","https://openalex.org/W4405492031","https://openalex.org/W4408135179"],"related_works":[],"abstract_inverted_index":{"Normalization":[0],"of":[1,11,16,23,39,73,87,96,138,173,201],"medical":[2,24,40,51,212],"concepts":[3],"to":[4,26,56,61,78,99,165,210],"an":[5,88],"ontology":[6,28,59,64,80,166],"is":[7],"a":[8,133,217,223],"key":[9],"aspect":[10],"the":[12,21,35,70,140,194,199],"natural":[13],"language":[14,44],"processing":[15],"biomedical":[17,152,195,228],"text.":[18],"It":[19],"enables":[20],"mapping":[22],"expressions":[25],"standardized":[27],"terms":[29,60,98,188],"and":[30,37,49,84,107,119,122,129,135,161],"their":[31,62,75,85],"identifiers,":[32],"thereby":[33],"enhancing":[34],"interoperability":[36],"computability":[38],"concepts.":[41,213],"Although":[42],"large":[43],"models":[45],"(LLMs)":[46],"can":[47,221],"identify":[48],"standardize":[50],"terms,":[52,167],"they":[53],"may":[54],"struggle":[55],"accurately":[57],"map":[58],"corresponding":[63],"identifiers.":[65],"These":[66],"challenges":[67],"arise":[68],"from":[69],"stochastic":[71],"nature":[72],"LLMs,":[74],"limited":[76],"exposure":[77,209],"uncommon":[79,211],"identifiers":[81],"during":[82],"training,":[83],"lack":[86],"integrated":[89],"lookup":[90],"mechanism.":[91],"We":[92,214],"generated":[93],"test":[94,141,219],"sets":[95],"synthetic":[97,218],"assess":[100],"normalization":[101,230],"performance":[102],"by":[103,156,170],"both":[104],"zero-shot":[105,183],"prompted":[106,111],"retrieval-augmented":[108],"generation":[109],"(RAG)":[110],"methods":[112],"across":[113,231],"two":[114,146],"ontologies":[115],"(Human":[116],"Phenotype":[117],"Ontology":[118],"Gene":[120],"Ontology)":[121],"three":[123],"LLMs":[124],"(GPT-4o,":[125],"LLaMA":[126],"3.3":[127],"70B,":[128],"Phi-4).":[130],"To":[131],"ensure":[132],"calibrated":[134],"fair":[136],"evaluation":[137],"normalization,":[139],"set":[142,220],"was":[143],"balanced":[144],"along":[145],"axes:":[147],"(1)":[148],"term":[149,229],"prevalence":[150],"in":[151,193,203,207],"literature,":[153],"as":[154,168],"estimated":[155],"PubMed":[157],"Central":[158],"frequency":[159],"counts,":[160],"(2)":[162],"semantic":[163],"proximity":[164],"assessed":[169],"cosine":[171],"similarity":[172],"BioBERT":[174],"embeddings.":[175],"Our":[176],"results":[177],"demonstrate":[178,215],"that":[179,189,216],"RAG":[180,202],"consistently":[181],"outperforms":[182],"prompting,":[184],"particularly":[185],"on":[186],"low-prevalence":[187],"are":[190],"infrequently":[191],"encountered":[192],"literature.":[196],"This":[197],"highlights":[198],"value":[200],"compensating":[204],"for":[205,226],"gaps":[206],"model":[208],"be":[222],"valuable":[224],"tool":[225],"evaluating":[227],"LLMs.":[232]},"counts_by_year":[],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}