{"id":"https://openalex.org/W4412886796","doi":"https://doi.org/10.18653/v1/2025.acl-long.111","title":"LL\u00e4Mmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch","display_name":"LL\u00e4Mmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886796","doi":"https://doi.org/10.18653/v1/2025.acl-long.111"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.111","pdf_url":"https://aclanthology.org/2025.acl-long.111.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.111.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043091880","display_name":"Jan Pfister","orcid":"https://orcid.org/0009-0006-8071-635X"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jan Pfister","raw_affiliation_strings":["Data Science Chair Center for Artificial Intelligence and Data Science (CAIDAS) Julius-Maximilians-Universitt Wrzburg (JMU )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Chair Center for Artificial Intelligence and Data Science (CAIDAS) Julius-Maximilians-Universitt Wrzburg (JMU )","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106007211","display_name":"Julia Wunderle","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Julia Wunderle","raw_affiliation_strings":["Data Science Chair Center for Artificial Intelligence and Data Science (CAIDAS) Julius-Maximilians-Universitt Wrzburg (JMU )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Chair Center for Artificial Intelligence and Data Science (CAIDAS) Julius-Maximilians-Universitt Wrzburg (JMU )","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054225034","display_name":"Andreas Hotho","orcid":"https://orcid.org/0000-0002-0483-5772"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andreas Hotho","raw_affiliation_strings":["Data Science Chair Center for Artificial Intelligence and Data Science (CAIDAS) Julius-Maximilians-Universitt Wrzburg (JMU )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Chair Center for Artificial Intelligence and Data Science (CAIDAS) Julius-Maximilians-Universitt Wrzburg (JMU )","institution_ids":["https://openalex.org/I4210164862"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08545958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2227","last_page":"2246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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":0.9262999892234802,"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/scratch","display_name":"Scratch","score":0.8390748500823975},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.7694216966629028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6683090925216675},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32963719964027405},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2830926477909088},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05336201190948486}],"concepts":[{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.8390748500823975},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7694216966629028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6683090925216675},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32963719964027405},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2830926477909088},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05336201190948486}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.111","pdf_url":"https://aclanthology.org/2025.acl-long.111.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.111","pdf_url":"https://aclanthology.org/2025.acl-long.111.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G180727766","display_name":null,"funder_award_id":"91b GG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3992037128","display_name":null,"funder_award_id":"440719683","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8281052048","display_name":"BERT mit Figur  Um Wissensgraphen angereicherte neuronale Sprachmodelle zur Analyse der Darstellung literarischer Figuren (LitBERT)","funder_award_id":"529659926","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/F4320325356","display_name":"Julius-Maximilians-Universit\u00e4t W\u00fcrzburg","ror":"https://ror.org/00fbnyb24"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886796.pdf","grobid_xml":"https://content.openalex.org/works/W4412886796.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4224247062"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623"],"abstract_inverted_index":{"We":[0],"transparently":[1],"create":[2],"two":[3],"German-only":[4],"decoder":[5],"models,":[6],"LLMmlein":[7,99],"120M":[8],"and":[9,15,76],"1B":[10],"1":[11],",":[12],"from":[13],"scratch":[14],"publish":[16],"them,":[17],"along":[18],"with":[19,108,119],"training":[20,33,48,67],"data,":[21],"for":[22,139],"the":[23,41,47,53,56,66,79,87,95,115],"(German)":[24],"NLP":[25],"research":[26],"community":[27],"to":[28,83,91],"use":[29],"2":[30],".The":[31],"model":[32],"involved":[34],"several":[35],"key":[36],"steps,":[37],"including":[38],"data":[39],"preprocessing/filtering,":[40],"creation":[42],"of":[43,55],"a":[44],"German":[45,80],"tokenizer,":[46],"itself,":[49],"as":[50,52,121],"well":[51],"evaluation":[54],"final":[57],"models":[58,93,100,107],"on":[59,94,126],"various":[60],"benchmarks,":[61],"also":[62],"against":[63],"existing":[64],"models.Throughout":[65],"process,":[68],"multiple":[69],"checkpoints":[70],"were":[71],"saved":[72],"in":[73],"equal":[74],"intervals":[75],"analyzed":[77],"using":[78],"SuperGLEBer":[81,96],"benchmark":[82],"gain":[84],"insights":[85,135],"into":[86,136],"models'":[88,116],"learning":[89],"process.Compared":[90],"state-of-the-art":[92],"benchmark,":[97],"both":[98],"performed":[101],"competitively,":[102],"consistently":[103],"matching":[104],"or":[105],"surpassing":[106],"similar":[109],"parameter":[110],"sizes.The":[111],"results":[112],"show":[113],"that":[114],"quality":[117],"scales":[118],"size":[120],"expected,":[122],"but":[123],"performance":[124],"improvements":[125],"some":[127],"tasks":[128],"plateaued":[129],"early":[130],"during":[131],"training,":[132],"offering":[133],"valuable":[134],"resource":[137],"allocation":[138],"future":[140],"models.":[141]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}