{"id":"https://openalex.org/W7203777454","doi":"https://doi.org/10.48550/arxiv.2608.17827","title":"From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sector","display_name":"From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sector","publication_year":2026,"publication_date":"2026-08-18","ids":{"openalex":"https://openalex.org/W7203777454","doi":"https://doi.org/10.48550/arxiv.2608.17827"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.17827","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17827","pdf_url":"https://arxiv.org/pdf/2608.17827","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","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/2608.17827","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008328565","display_name":"Camilla Dalerci","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210147761","display_name":"Bundesdruckerei (Germany)","ror":"https://ror.org/055jqqn57","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210147761"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dalerci, Camilla","raw_affiliation_strings":["Innovations Department , Bundesdruckerei GmbH , Berlin , Germany,","co-located with KONVENS 2026 in Hamburg , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovations Department , Bundesdruckerei GmbH , Berlin , Germany,","institution_ids":["https://openalex.org/I4210147761"]},{"raw_affiliation_string":"co-located with KONVENS 2026 in Hamburg , Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007929575","display_name":"Thilo Michael","orcid":"https://orcid.org/0000-0002-1086-6882","observed_orcids":["https://orcid.org/0000-0002-1086-6882"]},"institutions":[{"id":"https://openalex.org/I4210147761","display_name":"Bundesdruckerei (Germany)","ror":"https://ror.org/055jqqn57","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210147761"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael, Thilo","raw_affiliation_strings":["Innovations Department , Bundesdruckerei GmbH , Berlin , Germany,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovations Department , Bundesdruckerei GmbH , Berlin , Germany,","institution_ids":["https://openalex.org/I4210147761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070033839","display_name":"Robin Schaefer","orcid":"https://orcid.org/0000-0003-2904-3410","observed_orcids":["https://orcid.org/0000-0003-2904-3410"]},"institutions":[{"id":"https://openalex.org/I4210147761","display_name":"Bundesdruckerei (Germany)","ror":"https://ror.org/055jqqn57","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210147761"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Schaefer, Robin","raw_affiliation_strings":["Innovations Department , Bundesdruckerei GmbH , Berlin , Germany,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovations Department , Bundesdruckerei GmbH , Berlin , Germany,","institution_ids":["https://openalex.org/I4210147761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081588671","display_name":"Daniel Weinland","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210147761","display_name":"Bundesdruckerei (Germany)","ror":"https://ror.org/055jqqn57","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210147761"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Weinland, Daniel","raw_affiliation_strings":["Innovations Department , Bundesdruckerei GmbH , Berlin , Germany,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovations Department , Bundesdruckerei GmbH , Berlin , Germany,","institution_ids":["https://openalex.org/I4210147761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210147761"],"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.7979000210762024,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.7979000210762024,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.11020000278949738,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.015300000086426735,"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/large-language-models","display_name":"large language models","score":0.9240000247955322},{"id":"https://openalex.org/keywords/llm-benchmarking","display_name":"LLM benchmarking","score":0.7730000019073486},{"id":"https://openalex.org/keywords/german-public-sector","display_name":"German public sector","score":0.753000020980835},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"energy consumption","score":0.6370000243186951},{"id":"https://openalex.org/keywords/information-disclosure","display_name":"information disclosure","score":0.8149999976158142},{"id":"https://openalex.org/keywords/model-governance","display_name":"model governance","score":0.6209999918937683},{"id":"https://openalex.org/keywords/model-selection","display_name":"model selection","score":0.6690000295639038}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7703999876976013},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.758899986743927},{"id":"https://openalex.org/C39389867","wikidata":"https://www.wikidata.org/wiki/Q380767","display_name":"Corporate governance","level":2,"score":0.6762999892234802},{"id":"https://openalex.org/C147859227","wikidata":"https://www.wikidata.org/wiki/Q294217","display_name":"Public sector","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.5099999904632568},{"id":"https://openalex.org/C30772137","wikidata":"https://www.wikidata.org/wiki/Q5164762","display_name":"Consumption (sociology)","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C100001284","wikidata":"https://www.wikidata.org/wiki/Q2248246","display_name":"Public economics","level":1,"score":0.3813000023365021},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3452000021934509},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.2890999913215637},{"id":"https://openalex.org/C3116431","wikidata":"https://www.wikidata.org/wiki/Q31728","display_name":"Public administration","level":1,"score":0.28540000319480896},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.2689000070095062},{"id":"https://openalex.org/C148383697","wikidata":"https://www.wikidata.org/wiki/Q1781695","display_name":"Regional science","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C109986646","wikidata":"https://www.wikidata.org/wiki/Q546113","display_name":"Public policy","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C40700","wikidata":"https://www.wikidata.org/wiki/Q1411783","display_name":"Industrial organization","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.17827","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17827","pdf_url":"https://arxiv.org/pdf/2608.17827","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.17827","doi":"https://doi.org/10.48550/arxiv.2608.17827","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.17827","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.17827","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17827","pdf_url":"https://arxiv.org/pdf/2608.17827","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203777454.pdf","grobid_xml":"https://content.openalex.org/works/W7203777454.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7164511079","https://openalex.org/W7202173008","https://openalex.org/W7126051014","https://openalex.org/W7169813146","https://openalex.org/W7085494413","https://openalex.org/W4414094124","https://openalex.org/W4414890433","https://openalex.org/W7212340901","https://openalex.org/W7160552890","https://openalex.org/W4399695077"],"abstract_inverted_index":{"Public":[0],"institutions":[1,118],"face":[2],"a":[3,44],"persistent":[4],"challenge":[5],"in":[6],"selecting":[7],"LLMs":[8],"suited":[9],"to":[10],"their":[11],"specific":[12],"context.":[13,137],"Existing":[14],"benchmarks,":[15],"however,":[16],"are":[17],"of":[18,42,65,110,134],"limited":[19],"use":[20],"as":[21],"they":[22],"primarily":[23],"reflect":[24,130],"English-language":[25],"and":[26,29,63,88,102],"US-centric":[27],"settings,":[28],"often":[30],"only":[31],"evaluate":[32],"task":[33],"performance.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"present":[39],"first":[40],"results":[41,69],"M\u00d6VE,":[43],"holistic":[45],"evaluation":[46],"framework":[47],"for":[48,116],"the":[49,131,135],"German":[50,111],"public":[51,117],"sector,":[52],"examining":[53],"three":[54],"rarely":[55],"considered":[56],"governance":[57,132],"dimensions:":[58,80],"energy":[59,82],"consumption,":[60],"provider":[61],"transparency,":[62],"knowledge":[64,109],"German-party":[66],"positions.":[67,113],"Our":[68],"reveal":[70],"significant":[71],"trade-offs,":[72],"with":[73],"no":[74],"single":[75],"model":[76,93],"excelling":[77],"across":[78,100],"all":[79],"estimated":[81],"consumption":[83],"varies":[84,98],"more":[85],"than":[86],"60-fold":[87],"is":[89],"not":[90,106],"explained":[91],"by":[92],"size":[94],"alone,":[95],"information":[96],"disclosure":[97],"systematically":[99],"providers,":[101],"European":[103],"models":[104],"do":[105],"exhibit":[107],"stronger":[108],"party":[112],"Model":[114],"selection":[115],"thus":[119],"cannot":[120],"rely":[121],"on":[122],"performance":[123],"rankings":[124],"alone.":[125],"Instead,":[126],"evaluations":[127],"should":[128],"also":[129],"requirements":[133],"deployment":[136]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-20T00:00:00"}
