{"id":"https://openalex.org/W7169599298","doi":"https://doi.org/10.48550/arxiv.2607.14882","title":"Does generative AI supersede supervised XMLC? A Benchmark Study on Automated Subject Indexing with German Scientific Literature","display_name":"Does generative AI supersede supervised XMLC? A Benchmark Study on Automated Subject Indexing with German Scientific Literature","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7169599298","doi":"https://doi.org/10.48550/arxiv.2607.14882"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2607.14882","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.14882","pdf_url":"https://arxiv.org/pdf/2607.14882","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.14882","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091382296","display_name":"Maximilian K\u00e4hler","orcid":"https://orcid.org/0000-0003-4695-0565","observed_orcids":["https://orcid.org/0000-0003-4695-0565"]},"institutions":[{"id":"https://openalex.org/I4210110517","display_name":"Deutsche Nationalbibliothek","ror":"https://ror.org/01n7gem85","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210110517"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"K\u00e4hler, Maximilian","raw_affiliation_strings":["Deutsche Nationalbibliothek Leipzig/ Frankfurt am Main , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deutsche Nationalbibliothek Leipzig/ Frankfurt am Main , Germany","institution_ids":["https://openalex.org/I4210110517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141052404","display_name":"Katja Konermann","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210110517","display_name":"Deutsche Nationalbibliothek","ror":"https://ror.org/01n7gem85","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210110517"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Konermann, Katja","raw_affiliation_strings":["Deutsche Nationalbibliothek Leipzig/ Frankfurt am Main , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deutsche Nationalbibliothek Leipzig/ Frankfurt am Main , Germany","institution_ids":["https://openalex.org/I4210110517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120867129","display_name":"Lisa Kluge","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210110517","display_name":"Deutsche Nationalbibliothek","ror":"https://ror.org/01n7gem85","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210110517"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kluge, Lisa","raw_affiliation_strings":["Deutsche Nationalbibliothek Leipzig/ Frankfurt am Main , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deutsche Nationalbibliothek Leipzig/ Frankfurt am Main , Germany","institution_ids":["https://openalex.org/I4210110517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100845051","display_name":"Markus Schumacher","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210110517","display_name":"Deutsche Nationalbibliothek","ror":"https://ror.org/01n7gem85","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210110517"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Schumacher, Markus","raw_affiliation_strings":["Deutsche Nationalbibliothek Leipzig/ Frankfurt am Main , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deutsche Nationalbibliothek Leipzig/ Frankfurt am Main , Germany","institution_ids":["https://openalex.org/I4210110517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210110517"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.8490999937057495,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.8490999937057495,"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/T10028","display_name":"Topic Modeling","score":0.06539999693632126,"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/T14330","display_name":"Library Science and Information Systems","score":0.023000000044703484,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/extreme-multi-label-classification","display_name":"extreme multi-label classification","score":0.9620000123977661},{"id":"https://openalex.org/keywords/generative-ai","display_name":"generative AI","score":0.9300000071525574},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9810000061988831},{"id":"https://openalex.org/keywords/controlled-vocabulary","display_name":"controlled vocabulary","score":0.7720000147819519},{"id":"https://openalex.org/keywords/graded-relevance","display_name":"graded relevance","score":0.753000020980835},{"id":"https://openalex.org/keywords/library-cataloging","display_name":"library cataloging","score":0.5080000162124634},{"id":"https://openalex.org/keywords/german-national-library","display_name":"German National Library","score":0.8389999866485596}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.805899977684021},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.7599999904632568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6766999959945679},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6536999940872192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5644999742507935},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45500001311302185},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44119998812675476},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42590001225471497},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.35989999771118164},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26420000195503235},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2607.14882","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.14882","pdf_url":"https://arxiv.org/pdf/2607.14882","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2607.14882","doi":"https://doi.org/10.48550/arxiv.2607.14882","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.14882","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.14882","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.14882","pdf_url":"https://arxiv.org/pdf/2607.14882","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.6533213257789612,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7169599298.pdf","grobid_xml":"https://content.openalex.org/works/W7169599298.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415592502","https://openalex.org/W7202114391","https://openalex.org/W4414792145","https://openalex.org/W4404482174","https://openalex.org/W7092207799","https://openalex.org/W7026881100","https://openalex.org/W7112508473","https://openalex.org/W7160379617","https://openalex.org/W7221504640","https://openalex.org/W4417523722"],"abstract_inverted_index":{"With":[0],"a":[1,16,22,48,79,186],"large":[2],"controlled":[3],"vocabulary":[4],"as":[5,21,113,115],"the":[6,9,27,34,37,56,68,94,134,138,170,177],"label":[7],"set,":[8],"task":[10],"of":[11,29,50,59,86,137,157,173],"automated":[12],"subject":[13,30,60,121,139,175],"indexing":[14,61],"in":[15,101,155,169],"library":[17],"can":[18],"be":[19],"understood":[20],"multi-label":[23],"classification":[24],"task.":[25],"If":[26],"set":[28],"terms":[31,156],"is":[32,128],"large,":[33],"problem":[35],"fits":[36],"Extreme":[38],"Multi-Label":[39],"Classification":[40],"(XMLC)":[41],"objective.":[42],"In":[43],"this":[44],"study,":[45],"we":[46],"apply":[47],"selection":[49],"specialised":[51],"supervised":[52,144],"XMLC":[53,145],"methods":[54,92,127,180],"to":[55,129],"test":[57],"case":[58],"contemporary":[62],"German":[63,69],"scientific":[64],"literature,":[65],"collected":[66],"at":[67],"National":[70],"Library":[71],"(DNB).":[72],"We":[73,141],"contrast":[74],"these":[75],"results":[76,154],"by":[77,119],"including":[78],"classical":[80],"lexical":[81],"matching":[82],"baseline":[83],"and":[84,99,167],"three":[85],"our":[87,174],"own":[88],"recently":[89],"developed":[90],"LLM-based":[91,178],"into":[93],"benchmark.":[95],"Algorithms":[96],"are":[97],"evaluated":[98],"compared":[100],"several":[102],"metrics.":[103,161],"This":[104],"includes":[105],"binary":[106,159],"relevance":[107,117,160,166],"comparisons":[108],"with":[109],"previously":[110],"indexed":[111],"material,":[112],"well":[114],"graded":[116,165],"ratings":[118],"professional":[120],"librarians.":[122],"A":[123],"challenge":[124],"for":[125,189],"all":[126],"reliably":[130],"make":[131],"suggestions":[132],"from":[133],"long":[135,171],"tail":[136,172],"vocabulary.":[140],"find":[142],"that":[143],"algorithms":[146],"relying":[147],"on":[148,164],"transformer-based":[149],"dense":[150],"features":[151],"give":[152,181],"best":[153],"overall":[158],"However,":[162],"focusing":[163],"performance":[168],"vocabulary,":[176],"generative":[179],"better":[182],"results,":[183],"making":[184],"them":[185],"promising":[187],"alternative":[188],"future":[190],"productive":[191],"use.":[192]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-18T00:00:00"}