{"id":"https://openalex.org/W7140092850","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.15","title":"Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives","display_name":"Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140092850","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.15"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.15","pdf_url":"https://aclanthology.org/2026.findings-eacl.15.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.15.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130338773","display_name":"Yajiao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yajiao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027220244","display_name":"Congliang Chen","orcid":"https://orcid.org/0000-0002-9795-4200"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Congliang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130349415","display_name":"Junchi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junchi Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130333203","display_name":"Ruoyu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruoyu Sun","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.2696000039577484,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.2696000039577484,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.11659999936819077,"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":0.08060000091791153,"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-collection","display_name":"Data collection","score":0.30880001187324524},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.29490000009536743},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.289900004863739},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2793999910354614},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.26899999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5601000189781189},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3463999927043915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3328999876976013},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.2662000060081482},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.15","pdf_url":"https://aclanthology.org/2026.findings-eacl.15.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.15","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.15","pdf_url":"https://aclanthology.org/2026.findings-eacl.15.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7502267360687256,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140092850.pdf","grobid_xml":"https://content.openalex.org/works/W7140092850.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Training":[0],"large":[1],"language":[2],"models":[3],"with":[4,106],"data":[5,42,58,153],"collected":[6],"from":[7],"various":[8],"domains":[9,28,43],"can":[10,34],"improve":[11],"their":[12],"performance":[13],"on":[14],"downstream":[15],"tasks.However,":[16],"given":[17],"a":[18,53,63],"fixed":[19],"training":[20],"budget,":[21],"the":[22,31,37,46,71,107,115,130,138,150],"sampling":[23],"proportions":[24],"of":[25,56,66,123,142,152],"these":[26],"different":[27,41],"significantly":[29],"impact":[30],"model's":[32],"performance.How":[33],"we":[35,51,61,90,113,136],"determine":[36],"domain":[38],"weights":[39],"across":[40],"to":[44],"train":[45],"best-performing":[47],"model?In":[48],"this":[49],"paper,":[50],"provide":[52],"comprehensive":[54],"overview":[55],"existing":[57,67],"mixture":[59],"methods.First,":[60],"propose":[62],"fine-grained":[64],"categorization":[65],"methods,":[68,89,127],"extending":[69],"beyond":[70],"previous":[72],"offline":[73,111,124],"and":[74,84,101,125,128,132,140,145],"online":[75,88,98,126],"classification.Offline":[76],"methods":[77],"are":[78],"further":[79],"grouped":[80],"into":[81,93],"heuristicbased,":[82],"algorithm-based,":[83],"function":[85],"fittingbased":[86],"methods.For":[87],"categorize":[91],"them":[92],"three":[94],"groups-online":[95],"min-max":[96],"optimization,":[97],"mixing":[99],"law,":[100],"other":[102],"approaches-by":[103],"drawing":[104],"connections":[105],"optimization":[108],"frameworks":[109],"underlying":[110],"methods.Second,":[112],"summarize":[114],"problem":[116],"formulations,":[117],"representative":[118],"algorithms":[119],"for":[120],"each":[121,143],"subtype":[122],"clarify":[129],"relationships":[131],"distinctions":[133],"among":[134],"them.Finally,":[135],"discuss":[137],"advantages":[139],"disadvantages":[141],"method":[144],"highlight":[146],"key":[147],"challenges":[148],"in":[149],"field":[151],"mixture.":[154]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-24T00:00:00"}