{"id":"https://openalex.org/W4416767745","doi":"https://doi.org/10.1007/s13222-025-00519-3","title":"Historic to FAIR: Leveraging LLMs for Historic Term Identification and Standardization","display_name":"Historic to FAIR: Leveraging LLMs for Historic Term Identification and Standardization","publication_year":2025,"publication_date":"2025-11-01","ids":{"openalex":"https://openalex.org/W4416767745","doi":"https://doi.org/10.1007/s13222-025-00519-3"},"language":"en","primary_location":{"id":"doi:10.1007/s13222-025-00519-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-025-00519-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-025-00519-3.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s13222-025-00519-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092430235","display_name":"Jan Fillies","orcid":"https://orcid.org/0000-0002-2997-4656"},"institutions":[{"id":"https://openalex.org/I2800804238","display_name":"Fraunhofer Institute for Open Communication Systems","ror":"https://ror.org/00px80p03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800804238","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]},{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jan Fillies","raw_affiliation_strings":["Department: Informatik, Freie Universit\u00e4t Berlin, Berlin, Germany","FOKUS, Fraunhofer, Berlin, Germany","Institute for Applied Informatics (InfAI), University of Leipzig, Leipzig, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2997-4656","affiliations":[{"raw_affiliation_string":"Department: Informatik, Freie Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I75951250"]},{"raw_affiliation_string":"FOKUS, Fraunhofer, Berlin, Germany","institution_ids":["https://openalex.org/I2800804238"]},{"raw_affiliation_string":"Institute for Applied Informatics (InfAI), University of Leipzig, Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120022820","display_name":"Maximilian Teich","orcid":"https://orcid.org/0009-0000-7084-8291"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maximilian Teich","raw_affiliation_strings":["Chair of Computational Humanities, University of Passau, Passau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Computational Humanities, University of Passau, Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047005693","display_name":"Naouel Karam","orcid":"https://orcid.org/0000-0002-6762-6417"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Naouel Karam","raw_affiliation_strings":["Institute for Applied Informatics (InfAI), University of Leipzig, Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Applied Informatics (InfAI), University of Leipzig, Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088336451","display_name":"Adrian Paschke","orcid":"https://orcid.org/0000-0003-3156-9040"},"institutions":[{"id":"https://openalex.org/I2800804238","display_name":"Fraunhofer Institute for Open Communication Systems","ror":"https://ror.org/00px80p03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800804238","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]},{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adrian Paschke","raw_affiliation_strings":["Department: Informatik, Freie Universit\u00e4t Berlin, Berlin, Germany","FOKUS, Fraunhofer, Berlin, Germany","Institute for Applied Informatics (InfAI), University of Leipzig, Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department: Informatik, Freie Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I75951250"]},{"raw_affiliation_string":"FOKUS, Fraunhofer, Berlin, Germany","institution_ids":["https://openalex.org/I2800804238"]},{"raw_affiliation_string":"Institute for Applied Informatics (InfAI), University of Leipzig, Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020363123","display_name":"Malte Rehbein","orcid":"https://orcid.org/0000-0002-3252-0604"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Malte Rehbein","raw_affiliation_strings":["Chair of Computational Humanities, University of Passau, Passau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Computational Humanities, University of Passau, Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092430235"],"corresponding_institution_ids":["https://openalex.org/I2800804238","https://openalex.org/I75951250","https://openalex.org/I926574661"],"apc_list":{"value":2380,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2380,"currency":"EUR","value_usd":2890},"fwci":1.2871,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85154693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"25","issue":"3","first_page":"179","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10895","display_name":"Species Distribution and Climate Change","score":0.5331000089645386,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10895","display_name":"Species Distribution and Climate Change","score":0.5331000089645386,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.1200999990105629,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.08219999819993973,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.7523999810218811},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.6366000175476074},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.6119999885559082},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5656999945640564},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.4855000078678131},{"id":"https://openalex.org/keywords/semantic-interoperability","display_name":"Semantic interoperability","score":0.37439998984336853},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.3553999960422516}],"concepts":[{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.7523999810218811},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.6366000175476074},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5656999945640564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.503000020980835},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5015000104904175},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C192800085","wikidata":"https://www.wikidata.org/wiki/Q5258530","display_name":"Semantic interoperability","level":3,"score":0.37439998984336853},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C130217890","wikidata":"https://www.wikidata.org/wiki/Q47041","display_name":"Biodiversity","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.26170000433921814}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13222-025-00519-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-025-00519-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-025-00519-3.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s13222-025-00519-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-025-00519-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-025-00519-3.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5041172147","display_name":"NFDI4BioDiversit\u00e4t \u2013 Biodiversit\u00e4t, \u00d6kologie und Umweltdaten","funder_award_id":"442032008","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320324521","display_name":"Freie Universit\u00e4t Berlin","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416767745.pdf"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4230084628","https://openalex.org/W4367369313","https://openalex.org/W4399429879"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"As":[1],"the":[2,62,76,145,160,169,179,198],"availability":[3],"of":[4,64,80,91,135,144,168,181,202],"historical":[5,40,81,128,149,193],"biodiversity":[6,37,203],"data":[7,38,204],"continues":[8],"to":[9,16,104,147,184,191],"grow,":[10],"ensuring":[11],"its":[12],"usability":[13],"through":[14],"adherence":[15],"FAIR":[17,208],"principles":[18],"(Findable,":[19],"Accessible,":[20],"Interoperable,":[21],"and":[22,45,71,75,99,108,131,163,200],"Reusable)":[23],"has":[24],"become":[25],"increasingly":[26],"essential.":[27],"This":[28],"study":[29],"focuses":[30],"on":[31,138],"solving":[32],"key":[33],"challenges":[34,107],"in":[35,43,126,205],"interpreting":[36],"from":[39],"texts,":[41],"particularly":[42],"identifying":[44],"aligning":[46],"common":[47,129,150],"species":[48],"names":[49,130,151],"with":[50,152,207],"their":[51,102],"modern":[52,153],"scientific":[53,136],"counterparts.":[54],"We":[55],"address":[56],"five":[57,170],"main":[58],"challenges:":[59],"spelling":[60],"variations,":[61],"invention":[63],"new":[65],"terms,":[66],"semantic":[67],"shifts":[68],"between":[69],"broad":[70],"narrow":[72],"naming":[73,194],"conventions,":[74,195],"renaming":[77],"or":[78],"reclassification":[79],"terms.":[82],"To":[83],"tackle":[84],"these":[85,106],"issues,":[86],"we":[87],"tested":[88],"a":[89,122,139],"range":[90],"large":[92],"language":[93],"models":[94],"(LLMs)":[95],"(GPT\u20114,":[96],"LLaMA3-405B,":[97],"Mistral-8B,":[98],"Qwen3-30B-A3B)":[100],"for":[101],"ability":[103,146],"resolve":[105],"support":[109],"terminology":[110],"alignment.":[111],"The":[112,176],"initial":[113],"entity":[114],"detection":[115],"was":[116],"performed":[117],"using":[118],"GPT-4o,":[119],"which":[120],"achieved":[121],"92%":[123],"success":[124],"rate":[125],"detecting":[127],"correctly":[132],"identified":[133],"98%":[134],"terms":[137],"test":[140],"dataset.":[141],"Comparative":[142],"evaluation":[143],"match":[148],"equivalents":[154],"revealed":[155],"that":[156],"GPT-4o":[157],"consistently":[158],"delivered":[159],"most":[161],"accurate":[162],"nuanced":[164],"outputs":[165],"across":[166],"four":[167],"challenges,":[171],"demonstrating":[172],"strong":[173],"contextual":[174],"understanding.":[175],"results":[177],"highlight":[178],"potential":[180],"advanced":[182],"LLMs":[183],"not":[185],"only":[186],"identify":[187],"entities":[188],"but":[189],"also":[190],"interpret":[192],"thereby":[196],"enhancing":[197],"reusability":[199],"interoperability":[201],"line":[206],"principles.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-11-28T00:00:00"}
