{"id":"https://openalex.org/W4414745316","doi":"https://doi.org/10.48550/arxiv.2509.16914","title":"CUTE: A Multilingual Dataset for Enhancing Cross-Lingual Knowledge Transfer in Low-Resource Languages","display_name":"CUTE: A Multilingual Dataset for Enhancing Cross-Lingual Knowledge Transfer in Low-Resource Languages","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W4414745316","doi":"https://doi.org/10.48550/arxiv.2509.16914"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.16914","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.16914","pdf_url":"https://arxiv.org/pdf/2509.16914","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":"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/2509.16914","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029073999","display_name":"Wenhao Zhuang","orcid":"https://orcid.org/0009-0001-5474-2806","observed_orcids":["https://orcid.org/0009-0001-5474-2806","https://orcid.org/0009-0001-4224-0331"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Wenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101731298","display_name":"Yuan Sun","orcid":"https://orcid.org/0000-0003-0565-9659","observed_orcids":["https://orcid.org/0000-0003-0565-9659"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.9398999810218811,"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":0.9398999810218811,"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":0.05380000174045563,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0020000000949949026,"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-dataset","display_name":"multilingual dataset","score":0.652999997138977},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9150000214576721},{"id":"https://openalex.org/keywords/cross-lingual-knowledge-transfer","display_name":"cross-lingual knowledge transfer","score":0.9319999814033508},{"id":"https://openalex.org/keywords/cross-lingual-transfer-learning","display_name":"cross-lingual transfer learning","score":0.9079999923706055},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.5839999914169312},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.6639999747276306},{"id":"https://openalex.org/keywords/uyghur-language","display_name":"Uyghur language","score":0.8460000157356262},{"id":"https://openalex.org/keywords/tibetan-language","display_name":"Tibetan language","score":1.0},{"id":"https://openalex.org/keywords/chinese-language","display_name":"Chinese language","score":0.7950000166893005},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.824999988079071},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7390000224113464},{"id":"https://openalex.org/keywords/zero-shot-learning","display_name":"zero-shot learning","score":0.6830000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8420000076293945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7307999730110168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.654699981212616},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5960000157356262},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.47780001163482666},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2614000141620636},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2599000036716461}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.16914","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.16914","pdf_url":"https://arxiv.org/pdf/2509.16914","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.16914","doi":"https://doi.org/10.48550/arxiv.2509.16914","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.16914","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:2509.16914","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.16914","pdf_url":"https://arxiv.org/pdf/2509.16914","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7140158674","https://openalex.org/W4404649439","https://openalex.org/W7092285609","https://openalex.org/W4414846044","https://openalex.org/W4403752834","https://openalex.org/W7164495404","https://openalex.org/W7115177185","https://openalex.org/W4400064918","https://openalex.org/W4393726285","https://openalex.org/W7128432232"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"demonstrate":[4,124],"exceptional":[5],"zero-shot":[6],"capabilities":[7],"in":[8,127,142],"various":[9],"NLP":[10],"tasks,":[11],"significantly":[12],"enhancing":[13,128],"user":[14],"experience":[15],"and":[16,49,66,79,81,86,102,117,122,149],"efficiency.":[17],"However,":[18],"this":[19],"advantage":[20],"is":[21],"primarily":[22],"limited":[23],"to":[24,89,120,131,156],"resource-rich":[25,76],"languages.":[26],"For":[27],"the":[28,38,44,96,111,137,157],"diverse":[29],"array":[30],"of":[31,40,57,61,106,139],"low-resource":[32,83,133],"languages,":[33],"support":[34],"remains":[35],"inadequate,":[36],"with":[37],"scarcity":[39],"training":[41],"corpora":[42,63],"considered":[43],"primary":[45],"cause.":[46],"We":[47],"construct":[48],"open-source":[50,113],"CUTE":[51,73,109,147],"Chinese,":[52],"Uyghur,":[53],"Tibetan,English":[54],"dataset,":[55],"consisting":[56],"two":[58,75,82],"25GB":[59],"sets":[60],"four-language":[62],"(one":[64],"parallel":[65],"one":[67],"non-parallel),":[68],"obtained":[69],"through":[70],"machine":[71,97],"translation.":[72,108],"encompasses":[74],"languages":[77,84,119,134],"(Chinese":[78],"English)":[80],"(Uyghur":[85],"Tibetan).":[87],"Prior":[88],"constructing":[90],"CUTE,":[91],"human":[92],"assessment":[93],"validates":[94],"that":[95,105],"translation":[98],"quality":[99],"between":[100],"Chinese-Uyghur":[101],"Chinese-Tibetan":[103],"approaches":[104],"Chinese-English":[107],"represents":[110],"largest":[112],"corpus":[114,140,148],"for":[115],"Uyghur":[116],"Tibetan":[118],"date,":[121],"we":[123],"its":[125],"effectiveness":[126],"LLMs'":[129],"ability":[130],"process":[132],"while":[135],"investigating":[136],"role":[138],"parallelism":[141],"cross-lingual":[143],"transfer":[144],"learning.":[145],"The":[146],"related":[150],"models":[151],"are":[152],"made":[153],"publicly":[154],"available":[155],"research":[158],"community.":[159]},"counts_by_year":[],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2025-10-10T00:00:00"}