{"id":"https://openalex.org/W7201836807","doi":"https://doi.org/10.48550/arxiv.2608.05850","title":"MameLoshnLM: Yiddish Language Model and Evaluation Benchmark","display_name":"MameLoshnLM: Yiddish Language Model and Evaluation Benchmark","publication_year":2026,"publication_date":"2026-08-06","ids":{"openalex":"https://openalex.org/W7201836807","doi":"https://doi.org/10.48550/arxiv.2608.05850"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.05850","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.05850","pdf_url":"https://arxiv.org/pdf/2608.05850","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/2608.05850","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078037299","display_name":"Uri Katz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Katz, Uri","raw_affiliation_strings":["Bar-Ilan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153513926","display_name":"Omer Goldman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Goldman, Omer","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016443023","display_name":"Tomasz Limisiewicz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Limisiewicz, Tomasz","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063283689","display_name":"Reut Tsarfaty","orcid":"https://orcid.org/0000-0001-6406-6568","observed_orcids":["https://orcid.org/0000-0001-6406-6568"]},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Tsarfaty, Reut","raw_affiliation_strings":["Bar-Ilan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125194697","display_name":"Noah A. Smith","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Smith, Noah A.","raw_affiliation_strings":["Allen Institute for AI","University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8550000190734863,"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":0.8550000190734863,"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":0.13809999823570251,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0007999999797903001,"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/multilingual-language-models","display_name":"multilingual language models","score":0.6110000014305115},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8569999933242798},{"id":"https://openalex.org/keywords/yiddish-translation","display_name":"Yiddish translation","score":0.7099999785423279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476000189781189},{"id":"https://openalex.org/C26569328","wikidata":"https://www.wikidata.org/wiki/Q8641","display_name":"Yiddish","level":3,"score":0.7336000204086304},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7178000211715698},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6528000235557556},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.633899986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6104999780654907},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.41929998993873596},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.05850","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.05850","pdf_url":"https://arxiv.org/pdf/2608.05850","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.2608.05850","doi":"https://doi.org/10.48550/arxiv.2608.05850","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.05850","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.05850","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.05850","pdf_url":"https://arxiv.org/pdf/2608.05850","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/W7201836807.pdf","grobid_xml":"https://content.openalex.org/works/W7201836807.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7127415861","https://openalex.org/W7125819405","https://openalex.org/W7133903448","https://openalex.org/W4412889090","https://openalex.org/W4416036996","https://openalex.org/W4400519217","https://openalex.org/W7160206522","https://openalex.org/W7117558499","https://openalex.org/W4401042935","https://openalex.org/W2970193165"],"abstract_inverted_index":{"We":[0,57],"present":[1],"MameLoshnLM,":[2],"the":[3,23,46,104,107],"first":[4],"open-source":[5],"8B-parameter":[6],"language":[7,34,89,167],"model":[8,168],"built":[9],"specifically":[10],"for":[11,45,150,159,166],"Yiddish.":[12],"Despite":[13],"Yiddish's":[14],"rich":[15,172],"textual":[16],"tradition,":[17],"its":[18],"limited":[19],"digital":[20],"presence":[21],"and":[22,39,54,77,88,136,162],"scarcity":[24],"of":[25,51,113,145],"reliable":[26],"evaluation":[27],"resources":[28],"have":[29],"constrained":[30],"progress":[31],"in":[32,106,170],"Yiddish":[33,66,160],"modeling.":[35],"Existing":[36],"multilingual":[37,129,148],"corpora":[38],"benchmarks":[40],"are":[41,122],"often":[42],"poor":[43],"proxies":[44],"language,":[47],"containing":[48],"substantial":[49],"amounts":[50],"noisy,":[52],"machine-translated,":[53],"misclassified":[55],"text.":[56],"address":[58],"these":[59,92,120],"gaps":[60],"by":[61],"introducing":[62],"Oytser,":[63],"a":[64,79,141,157,163],"high-quality":[65],"pretraining":[67,96],"corpus":[68],"that":[69,119],"combines":[70],"contemporary":[71],"web-native":[72],"sources":[73],"with":[74],"literary":[75],"materials,":[76],"Kashes,":[78],"multi-task":[80],"benchmark":[81],"spanning":[82],"translation,":[83],"linguistic":[84],"analysis,":[85],"information":[86],"extraction,":[87],"understanding.":[90],"Using":[91],"resources,":[93],"we":[94],"continue":[95],"Llama":[97],"3.1":[98],"8B":[99],"to":[100,127,140],"obtain":[101],"MameLoshnLM.":[102],"Across":[103],"tasks":[105],"benchmark,":[108],"MameLoshnLM":[109,131],"outperforms":[110],"open":[111],"baselines":[112],"similar":[114],"scale.":[115],"Our":[116,153],"analyses":[117],"show":[118],"gains":[121],"not":[123],"only":[124],"quantitative:":[125],"relative":[126],"general-purpose":[128],"models,":[130],"better":[132],"captures":[133],"language-defining":[134],"lexical":[135],"morphological":[137],"patterns,":[138],"pointing":[139],"broader":[142],"failure":[143],"mode":[144],"noisy":[146],"web-scale":[147],"data":[149],"low-resource":[151],"languages.":[152,176],"results":[154],"provide":[155],"both":[156],"foundation":[158],"NLP":[161],"practical":[164],"template":[165],"development":[169],"historically":[171],"but":[173],"digitally":[174],"underrepresented":[175]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-08T00:00:00"}
