{"id":"https://openalex.org/W7140131732","doi":"https://doi.org/10.18653/v1/2026.eacl-long.58","title":"Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation","display_name":"Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140131732","doi":"https://doi.org/10.18653/v1/2026.eacl-long.58"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.58","pdf_url":"https://aclanthology.org/2026.eacl-long.58.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.58.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042575470","display_name":"Thomas F Burns","orcid":"https://orcid.org/0000-0002-1123-2929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas F Burns","raw_affiliation_strings":["Aleph Alpha Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aleph Alpha Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130392165","display_name":"Letitia Parcalabescu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Letitia Parcalabescu","raw_affiliation_strings":["Aleph Alpha Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aleph Alpha Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130356472","display_name":"Stephan Waeldchen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephan Waeldchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130383719","display_name":"Michael Barlow","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Barlow","raw_affiliation_strings":["Aleph Alpha Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aleph Alpha Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130344411","display_name":"Gregor Ziegltrum","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gregor Ziegltrum","raw_affiliation_strings":["Aleph Alpha Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aleph Alpha Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130373470","display_name":"Volker Stampa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Volker Stampa","raw_affiliation_strings":["Aleph Alpha Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aleph Alpha Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024191282","display_name":"Bastian Harren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bastian Harren","raw_affiliation_strings":["Aleph Alpha Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aleph Alpha Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130336600","display_name":"Bj\u00f6rn Deiseroth","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Deiseroth","raw_affiliation_strings":["Aleph Alpha Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aleph Alpha Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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":0.39992155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1267","last_page":"1283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8137999773025513,"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":0.8137999773025513,"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":0.0860000029206276,"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/T13629","display_name":"Text Readability and Simplification","score":0.02410000003874302,"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/data-curation","display_name":"Data curation","score":0.6761000156402588},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.32010000944137573},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.3073999881744385},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.2800999879837036},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.27799999713897705},{"id":"https://openalex.org/keywords/data-conversion","display_name":"Data conversion","score":0.2619999945163727}],"concepts":[{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.6761000156402588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6115999817848206},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C1232282","wikidata":"https://www.wikidata.org/wiki/Q1783551","display_name":"Data conversion","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C2776904630","wikidata":"https://www.wikidata.org/wiki/Q356336","display_name":"Adept","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C104582849","wikidata":"https://www.wikidata.org/wiki/Q787282","display_name":"Automatic identification and data capture","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.58","pdf_url":"https://aclanthology.org/2026.eacl-long.58.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.00022","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.00022","pdf_url":"https://arxiv.org/pdf/2505.00022","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.58","pdf_url":"https://aclanthology.org/2026.eacl-long.58.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100289225578308,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140131732.pdf","grobid_xml":"https://content.openalex.org/works/W7140131732.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Thomas":[0],"F":[1],"Burns,":[2],"Letitia":[3],"Parcalabescu,":[4],"Stephan":[5],"Waeldchen,":[6],"Michael":[7],"Barlow,":[8],"Gregor":[9],"Ziegltrum,":[10],"Volker":[11],"Stampa,":[12],"Bastian":[13],"Harren,":[14],"Bj\u00f6rn":[15],"Deiseroth.":[16],"Proceedings":[17],"of":[18,22,26],"the":[19,23,27],"19th":[20],"Conference":[21],"European":[24],"Chapter":[25],"Association":[28],"for":[29],"Computational":[30],"Linguistics":[31],"(Volume":[32],"1:":[33],"Long":[34],"Papers).":[35],"2026.":[36]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}