{"id":"https://openalex.org/W4414697893","doi":"https://doi.org/10.1145/3805712.3809946","title":"M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets","display_name":"M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W4414697893","doi":"https://doi.org/10.1145/3805712.3809946"},"language":"en","primary_location":{"id":"doi:10.1145/3805712.3809946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3805712.3809946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.15549","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102602151","display_name":"Chunguang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunguang Zhao","raw_affiliation_strings":["Huawei Technologies Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-5501-2105","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669852","display_name":"Yilun Liu","orcid":"https://orcid.org/0000-0001-8828-9432"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilun Liu","raw_affiliation_strings":["Huawei Technologies Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-2531-7728","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060490057","display_name":"Pufan Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pufan Zeng","raw_affiliation_strings":["University of Science and Technology of China, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-6256-6315","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Suzhou, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113392186","display_name":"Yuanchang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchang Luo","raw_affiliation_strings":["Huawei Technologies Ltd., Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0001-4411-462X","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Xi'an, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006709668","display_name":"Shimin Tao","orcid":"https://orcid.org/0000-0002-2795-6921"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Tao","raw_affiliation_strings":["Huawei Technologies Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2795-6921","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108150655","display_name":"M. He","orcid":"https://orcid.org/0009-0002-0589-4966"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minggui He","raw_affiliation_strings":["Huawei Technologies Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-4719-6241","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027448460","display_name":"Weibin Meng","orcid":"https://orcid.org/0000-0002-9384-9016"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibin Meng","raw_affiliation_strings":["Huawei Technologies Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9384-9016","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034903351","display_name":"Song Hua Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Xu","raw_affiliation_strings":["University of Science and Technology of China, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-1917-1931","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Suzhou, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100322136","display_name":"Chen Liu","orcid":"https://orcid.org/0000-0001-9652-2441"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Liu","raw_affiliation_strings":["Huawei Technologies Ltd., Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-2697-5195","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Nanjing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595300","display_name":"Hongxia Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxia Ma","raw_affiliation_strings":["Huawei Technologies Ltd., Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-1046-4477","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Nanjing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425448","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-7914-0679"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Huawei Technologies Ltd., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-6392-4589","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019715118","display_name":"Boxing Chen","orcid":"https://orcid.org/0000-0002-3170-4858"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Boxing Chen","raw_affiliation_strings":["Huawei Technologies Ltd., Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3170-4858","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Montreal, Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019715118","display_name":"Boxing Chen","orcid":"https://orcid.org/0000-0002-3170-4858"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daimeng Wei","raw_affiliation_strings":["Huawei Technologies Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9606-5058","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":"4361","last_page":"4366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.9559000134468079,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11122","display_name":"Online Learning and Analytics","score":0.9559000134468079,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/heuristics","display_name":"Heuristics","score":0.7303000092506409},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5776000022888184},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5672000050544739},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.5288000106811523},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.5145000219345093},{"id":"https://openalex.org/keywords/cultural-diversity","display_name":"Cultural diversity","score":0.4652000069618225},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42489999532699585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516999840736389},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7303000092506409},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5672000050544739},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.5145000219345093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49889999628067017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4772000014781952},{"id":"https://openalex.org/C125209646","wikidata":"https://www.wikidata.org/wiki/Q1338878","display_name":"Cultural diversity","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42489999532699585},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3765999972820282},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C2992249680","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Linguistic diversity","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2793999910354614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2644999921321869}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3805712.3809946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3805712.3809946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.15549","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.15549","pdf_url":"https://arxiv.org/pdf/2509.15549","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"pmh:oai:arXiv.org:2509.15549","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.15549","pdf_url":"https://arxiv.org/pdf/2509.15549","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.15549","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.15549","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.15549","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.15549","pdf_url":"https://arxiv.org/pdf/2509.15549","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multilingual":[0],"instruction":[1],"fine-tuning":[2],"(IFT)":[3],"empowers":[4],"large":[5],"language":[6],"models":[7,91],"to":[8,63,131],"generalize":[9],"across":[10,86],"diverse":[11],"linguistic":[12],"and":[13,34,45,107,123,134],"cultural":[14,119],"contexts;":[15],"however,":[16],"high-quality,":[17],"systematically":[18],"curated":[19],"multilingual":[20,82],"IFT":[21],"datasets":[22],"remain":[23],"scarce.":[24],"To":[25],"address":[26],"this":[27],"gap,":[28],"we":[29,70],"propose":[30],"M-DaQ":[31,49],"(Multilingual":[32],"Diversity":[33],"Quality),":[35],"a":[36,51,57],"diversity-aware":[37],"sampling":[38],"framework":[39],"that":[40,90],"jointly":[41],"optimizes":[42],"instruction-response":[43],"quality":[44],"cross-lingual":[46],"semantic":[47],"diversity.":[48],"leverages":[50],"fine-tuned":[52],"Quality":[53],"Scoring":[54],"Model":[55],"alongside":[56],"maximal":[58],"marginal":[59],"relevance-inspired":[60],"selection":[61],"strategy":[62],"construct":[64],"balanced,":[65],"high-fidelity":[66],"training":[67],"data.":[68],"Furthermore,":[69],"present":[71],"the":[72,77],"first":[73],"systematic":[74],"investigation":[75],"of":[76],"Superficial":[78],"Alignment":[79],"Hypothesis":[80],"in":[81,118],"settings.":[83],"Extensive":[84],"evaluations":[85,111],"18":[87],"languages":[88],"demonstrate":[89],"trained":[92],"on":[93,105],"M-DaQ-curated":[94],"data":[95],"achieve":[96],"average":[97],"win":[98],"rates":[99],"exceeding":[100],"60%":[101],"against":[102],"strong":[103],"baselines":[104],"Alpaca-Eval":[106],"MT-Bench.":[108],"Complementary":[109],"human":[110],"corroborate":[112],"these":[113],"gains,":[114],"highlighting":[115],"significant":[116],"improvements":[117],"relevance,":[120],"contextual":[121],"appropriateness,":[122],"instruction-following":[124],"capability.":[125],"The":[126],"code":[127],"are":[128],"publicly":[129],"released":[130],"facilitate":[132],"reproducibility":[133],"future":[135],"research.":[136]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2025-10-10T00:00:00"}