{"id":"https://openalex.org/W4415318014","doi":"https://doi.org/10.48550/arxiv.2510.07074","title":"LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish","display_name":"LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish","publication_year":2025,"publication_date":"2025-10-08","ids":{"openalex":"https://openalex.org/W4415318014","doi":"https://doi.org/10.48550/arxiv.2510.07074"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.07074","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.07074","pdf_url":"https://arxiv.org/pdf/2510.07074","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","license_id":"https://openalex.org/licenses/cc-by","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/2510.07074","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018702042","display_name":"Fred Philippy","orcid":"https://orcid.org/0000-0001-5842-4285","observed_orcids":["https://orcid.org/0000-0001-5842-4285"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4405259781","display_name":"Interdisciplinary Centre for Security, Reliability and Trust","ror":"https://ror.org/02qav7c04","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Philippy, Fred","raw_affiliation_strings":["SnT , University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SnT , University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119466100","display_name":"Laura Bernardy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4405259781","display_name":"Interdisciplinary Centre for Security, Reliability and Trust","ror":"https://ror.org/02qav7c04","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Bernardy, Laura","raw_affiliation_strings":["SnT , University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SnT , University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102370003","display_name":"Siwen Guo","orcid":"https://orcid.org/0009-0004-1670-1837","observed_orcids":["https://orcid.org/0009-0004-1670-1837"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Siwen","raw_affiliation_strings":["Zortify Labs , Zortify S.A. , Luxembourg ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zortify Labs , Zortify S.A. , Luxembourg ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040326968","display_name":"Jacques Klein","orcid":"https://orcid.org/0000-0003-4052-475X","observed_orcids":["https://orcid.org/0000-0003-4052-475X"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4405259781","display_name":"Interdisciplinary Centre for Security, Reliability and Trust","ror":"https://ror.org/02qav7c04","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Klein, Jacques","raw_affiliation_strings":["SnT , University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SnT , University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082835974","display_name":"Tegawend\u00e9 Fran\u00e7ois Bissyand\u00e9","orcid":"https://orcid.org/0000-0001-7270-9869","observed_orcids":["https://orcid.org/0000-0001-7270-9869"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]},{"id":"https://openalex.org/I4405259781","display_name":"Interdisciplinary Centre for Security, Reliability and Trust","ror":"https://ror.org/02qav7c04","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Bissyand\u00e9, Tegawend\u00e9 F.","raw_affiliation_strings":["SnT , University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SnT , University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577","https://openalex.org/I4405259781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.5551999807357788,"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":0.5551999807357788,"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":0.4154999852180481,"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":0.012400000356137753,"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/luxembourgish","display_name":"Luxembourgish","score":0.8370000123977661},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.7960000038146973},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9879999756813049},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6650000214576721},{"id":"https://openalex.org/keywords/data-alignment","display_name":"data alignment","score":0.43299999833106995},{"id":"https://openalex.org/keywords/machine-translation-limitations","display_name":"machine translation limitations","score":0.6520000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731999754905701},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44920000433921814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44609999656677246},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.31439998745918274},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.25600001215934753},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.07074","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.07074","pdf_url":"https://arxiv.org/pdf/2510.07074","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.07074","doi":"https://doi.org/10.48550/arxiv.2510.07074","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.07074","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.07074","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.07074","pdf_url":"https://arxiv.org/pdf/2510.07074","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415318014.pdf","grobid_xml":"https://content.openalex.org/works/W4415318014.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7102399629","https://openalex.org/W4402670730","https://openalex.org/W4413952839","https://openalex.org/W4388748025","https://openalex.org/W4407764926","https://openalex.org/W6948249650","https://openalex.org/W4386554933","https://openalex.org/W4388890640","https://openalex.org/W4402670821","https://openalex.org/W4392669894"],"abstract_inverted_index":{"Instruction":[0],"tuning":[1,63,101],"has":[2],"become":[3],"a":[4,60,86],"key":[5],"technique":[6],"for":[7,65],"enhancing":[8],"the":[9,33,111,125],"performance":[10],"of":[11,35,128],"large":[12],"language":[13,135],"models,":[14],"enabling":[15],"them":[16],"to":[17,32,69],"better":[18],"follow":[19],"human":[20],"prompts.":[21],"However,":[22],"low-resource":[23,134],"languages":[24,108],"such":[25],"as":[26],"Luxembourgish":[27],"face":[28],"severe":[29],"limitations":[30],"due":[31],"lack":[34],"high-quality":[36,87],"instruction":[37,62,100],"datasets.":[38],"Traditional":[39],"reliance":[40],"on":[41],"machine":[42],"translation":[43],"often":[44],"introduces":[45],"semantic":[46],"misalignment":[47],"and":[48,82,92,131],"cultural":[49,93],"inaccuracies.":[50],"In":[51],"this":[52],"work,":[53],"we":[54,84],"address":[55],"these":[56],"challenges":[57],"by":[58,75],"creating":[59],"cross-lingual":[61,99,120],"dataset":[64,88],"Luxembourgish,":[66],"without":[67],"resorting":[68],"machine-generated":[70],"translations":[71],"into":[72],"it.":[73],"Instead,":[74],"leveraging":[76],"aligned":[77],"data":[78,121,130],"from":[79],"English,":[80],"French,":[81],"German,":[83],"build":[85],"that":[89,98],"preserves":[90],"linguistic":[91],"nuances.":[94],"We":[95],"provide":[96],"evidence":[97],"not":[102],"only":[103],"improves":[104],"representational":[105],"alignment":[106],"across":[107],"but":[109],"also":[110],"model's":[112],"generative":[113],"capabilities":[114],"in":[115],"Luxembourgish.":[116],"This":[117],"highlights":[118],"how":[119],"curation":[122],"can":[123],"avoid":[124],"common":[126],"pitfalls":[127],"machine-translated":[129],"directly":[132],"benefit":[133],"development.":[136]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-18T00:00:00"}
