{"id":"https://openalex.org/W4414097106","doi":"https://doi.org/10.3390/info16090776","title":"Prior Knowledge Shapes Success When Large Language Models Are Fine-Tuned for Biomedical Term Normalization","display_name":"Prior Knowledge Shapes Success When Large Language Models Are Fine-Tuned for Biomedical Term Normalization","publication_year":2025,"publication_date":"2025-09-07","ids":{"openalex":"https://openalex.org/W4414097106","doi":"https://doi.org/10.3390/info16090776"},"language":"en","primary_location":{"id":"doi:10.3390/info16090776","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16090776","pdf_url":"https://www.mdpi.com/2078-2489/16/9/776/pdf?version=1757326871","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/16/9/776/pdf?version=1757326871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046843425","display_name":"Daniel B. Hier","orcid":"https://orcid.org/0000-0002-6179-0793"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel B. Hier","raw_affiliation_strings":["Department of Neurology & Rehabilitation, University of Illinois at Chicago, Chicago, IL 60612, USA"],"raw_orcid":"https://orcid.org/0000-0002-6179-0793","affiliations":[{"raw_affiliation_string":"Department of Neurology & Rehabilitation, University of Illinois at Chicago, Chicago, IL 60612, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083683344","display_name":"Steven Keith Platt","orcid":"https://orcid.org/0000-0001-8270-1932"},"institutions":[{"id":"https://openalex.org/I1925986","display_name":"Loyola University Chicago","ror":"https://ror.org/04b6x2g63","country_code":"US","type":"education","lineage":["https://openalex.org/I1925986"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven K. Platt","raw_affiliation_strings":["Laboratory for Applied Artificial Intelligence, Loyola University Chicago, Chicago, IL 60611, USA"],"raw_orcid":"https://orcid.org/0000-0001-8270-1932","affiliations":[{"raw_affiliation_string":"Laboratory for Applied Artificial Intelligence, Loyola University Chicago, Chicago, IL 60611, USA","institution_ids":["https://openalex.org/I1925986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111419339","display_name":"Anh Nguyen","orcid":"https://orcid.org/0009-0001-8836-7944"},"institutions":[{"id":"https://openalex.org/I1925986","display_name":"Loyola University Chicago","ror":"https://ror.org/04b6x2g63","country_code":"US","type":"education","lineage":["https://openalex.org/I1925986"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anh Nguyen","raw_affiliation_strings":["Laboratory for Applied Artificial Intelligence, Loyola University Chicago, Chicago, IL 60611, USA"],"raw_orcid":"https://orcid.org/0009-0001-8836-7944","affiliations":[{"raw_affiliation_string":"Laboratory for Applied Artificial Intelligence, Loyola University Chicago, Chicago, IL 60611, USA","institution_ids":["https://openalex.org/I1925986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046843425"],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.4868,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66561935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"16","issue":"9","first_page":"776","last_page":"776"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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":0.980400025844574,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.6786999702453613},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5789999961853027},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5156000256538391},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5145999789237976},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5142999887466431},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.4300999939441681},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4049000144004822},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.36010000109672546}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6786999702453613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6699000000953674},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5789999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.550599992275238},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5156000256538391},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4708999991416931},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4189000129699707},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4049000144004822},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2603999972343445}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info16090776","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16090776","pdf_url":"https://www.mdpi.com/2078-2489/16/9/776/pdf?version=1757326871","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:33c143ce120d4d2abdedc32e1feaabde","is_oa":true,"landing_page_url":"https://doaj.org/article/33c143ce120d4d2abdedc32e1feaabde","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 16, Iss 9, p 776 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info16090776","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16090776","pdf_url":"https://www.mdpi.com/2078-2489/16/9/776/pdf?version=1757326871","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6064844482","display_name":"XTRIPODS: Loyola University Chicago-Lab for Applied Artificial Intelligence","funder_award_id":"2423235","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414097106.pdf","grobid_xml":"https://content.openalex.org/works/W4414097106.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1996564262","https://openalex.org/W2025349319","https://openalex.org/W2039612385","https://openalex.org/W2101680936","https://openalex.org/W2119613819","https://openalex.org/W2127479124","https://openalex.org/W2136410628","https://openalex.org/W2162151166","https://openalex.org/W2557385283","https://openalex.org/W2768488789","https://openalex.org/W2950595506","https://openalex.org/W3048179169","https://openalex.org/W3119641321","https://openalex.org/W3168867926","https://openalex.org/W3173667512","https://openalex.org/W3212714602","https://openalex.org/W4318983406","https://openalex.org/W4322766882","https://openalex.org/W4365511667","https://openalex.org/W4378509449","https://openalex.org/W4385245566","https://openalex.org/W4391973028","https://openalex.org/W4399280731","https://openalex.org/W4400524651","https://openalex.org/W4403587126","https://openalex.org/W4404782801","https://openalex.org/W4405934528","https://openalex.org/W4409638049","https://openalex.org/W4410973732","https://openalex.org/W4411119969","https://openalex.org/W4412082603","https://openalex.org/W4412453082"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"often":[4],"fail":[5],"to":[6],"correctly":[7],"associate":[8],"biomedical":[9,138],"terms":[10,59,169,227],"with":[11,181],"their":[12],"standardized":[13],"ontology":[14],"identifiers,":[15],"posing":[16],"challenges":[17],"for":[18,145,168],"downstream":[19],"applications":[20],"that":[21,71,187,243],"rely":[22],"on":[23,63,251],"accurate,":[24],"machine-readable":[25],"codes.":[26],"These":[27,226],"linking":[28,89],"failures":[29],"can":[30,47],"compromise":[31],"the":[32,53,64,137,158,174,179,229,233,244,252,259],"integrity":[33],"of":[34,55,76,125,154,160,178,184,246,254],"data":[35],"used":[36],"in":[37,95,112,120,136,170,238,258],"precision":[38],"medicine,":[39],"clinical":[40],"decision":[41],"support,":[42],"and":[43,60,128],"population":[44],"health.":[45],"Fine-tuning":[46,164,194],"partially":[48],"remedy":[49],"these":[50,152],"issues,":[51],"but":[52,122],"degree":[54],"improvement":[56],"varies":[57,166],"across":[58],"terminologies.":[61],"Focusing":[62],"Human":[65],"Phenotype":[66],"Ontology":[67],"(HPO),":[68],"we":[69,172],"show":[70],"a":[72,143],"model\u2019s":[73],"prior":[74,93,155,185,199,213],"knowledge":[75,94,156,186,200,214,220,247,257],"term\u2013identifier":[77,255],"pairs,":[78],"acquired":[79],"during":[80,240],"pre-training,":[81],"strongly":[82],"predicts":[83],"whether":[84],"fine-tuning":[85],"will":[86],"enhance":[87],"its":[88],"accuracy.":[90],"We":[91,148],"evaluate":[92],"three":[96],"complementary":[97],"ways:":[98],"(1)":[99],"latent":[100,218],"probabilistic":[101,219],"knowledge,":[102,118,206],"revealed":[103],"through":[104],"stochastic":[105],"prompting,":[106],"captures":[107],"hidden":[108],"associations":[109],"not":[110],"evident":[111],"deterministic":[113,161],"output;":[114],"(2)":[115],"partial":[116,204],"subtoken":[117,205],"reflected":[119],"incomplete":[121],"non-random":[123],"generation":[124],"identifier":[126,162],"components;":[127],"(3)":[129],"term":[130],"familiarity,":[131],"inferred":[132],"from":[133,228],"annotation":[134],"frequencies":[135],"literature,":[139],"which":[140],"serve":[141],"as":[142,201,215],"proxy":[144],"training":[146],"exposure.":[147],"then":[149],"assess":[150],"how":[151],"forms":[153],"influence":[157],"accuracy":[159,239],"linking.":[163],"performance":[165],"most":[167,196],"what":[171],"call":[173],"reactive":[175],"middle":[176],"zone":[177],"ontology\u2014terms":[180],"intermediate":[182],"levels":[183],"are":[188],"neither":[189],"absent":[190],"nor":[191],"fully":[192],"consolidated.":[193],"was":[195,207,221],"successful":[197],"when":[198,212],"measured":[202,216],"by":[203,217],"\u2018weak\u2019":[208,224],"or":[209,211,223,236],"\u2018medium\u2019":[210],"\u2018unknown\u2019":[222],"(p<0.001).":[225],"\u2018reactive":[230],"middle\u2019":[231],"exhibited":[232],"largest":[234],"gains":[235],"losses":[237],"fine-tuning,":[241],"suggesting":[242],"success":[245],"injection":[248],"critically":[249],"depends":[250],"level":[253],"pair":[256],"LLM":[260],"before":[261],"fine-tuning.":[262]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}