{"id":"https://openalex.org/W7166797593","doi":"https://doi.org/10.18653/v1/2026.findings-acl.643","title":"Empirical Analysis of Task Mixture Effects in Small-scale Instruction Tuning: A Statistical Approach","display_name":"Empirical Analysis of Task Mixture Effects in Small-scale Instruction Tuning: A Statistical Approach","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166797593","doi":"https://doi.org/10.18653/v1/2026.findings-acl.643"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.643","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.643","pdf_url":"https://aclanthology.org/2026.findings-acl.643.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: ACL 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-acl.643.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052038058","display_name":"Jeesu Jung","orcid":"https://orcid.org/0000-0003-1684-0517"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeesu Jung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129738545","display_name":"Sangkeun Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangkeun Jung","raw_affiliation_strings":["Chungnam National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chungnam National University","institution_ids":["https://openalex.org/I196345858"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8799639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13168","last_page":"13186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10826","display_name":"Behavioral and Psychological Studies","score":0.2563999891281128,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10826","display_name":"Behavioral and Psychological Studies","score":0.2563999891281128,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11516","display_name":"Visual and Cognitive Learning Processes","score":0.17229999601840973,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.06589999794960022,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5475000143051147},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.3831000030040741},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.34459999203681946},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.2858000099658966},{"id":"https://openalex.org/keywords/statistical-learning","display_name":"Statistical learning","score":0.2741999924182892},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.27059999108314514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5852000117301941},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5475000143051147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4738999903202057},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C97933134","wikidata":"https://www.wikidata.org/wiki/Q5374249","display_name":"Empirical probability","level":4,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.643","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.643","pdf_url":"https://aclanthology.org/2026.findings-acl.643.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.643","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.643","pdf_url":"https://aclanthology.org/2026.findings-acl.643.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1274038710","display_name":null,"funder_award_id":"RS-2019-II190004","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3172531149","display_name":null,"funder_award_id":"RS-2025-0055621731482092640101","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3204065847","display_name":null,"funder_award_id":"RS-2025-25464461","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4513902197","display_name":null,"funder_award_id":"RS-2025-0055621731482092640101","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4660618921","display_name":null,"funder_award_id":"RS-2019-II190004","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6529730756","display_name":null,"funder_award_id":"RS-2024-00445087","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8386376097","display_name":null,"funder_award_id":"26212MFDS008","funder_id":"https://openalex.org/F4320322014","funder_display_name":"Ministry of Food and Drug Safety"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322014","display_name":"Ministry of Food and Drug Safety","ror":"https://ror.org/01f7dp456"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166797593.pdf","grobid_xml":"https://content.openalex.org/works/W7166797593.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"performance":[1],"of":[2,35,66],"large":[3],"language":[4],"models":[5],"heavily":[6,44],"depends":[7],"on":[8,12,23,45,56],"instruction":[9,58],"tuning,":[10],"especially":[11],"task":[13,67,104],"types":[14],"and":[15,32,64,90,127,145],"mixture":[16,139],"ratios.However,":[17],"previous":[18],"research":[19],"has":[20,42],"primarily":[21],"focused":[22],"mixing":[24],"tasks":[25],"at":[26],"fixed":[27],"ratios,":[28],"lacking":[29],"a":[30,94],"systematic":[31],"quantitative":[33],"analysis":[34],"task-wise":[36],"interactions":[37,119],"across":[38],"diverse":[39],"tasks.Moreover,":[40],"it":[41],"relied":[43],"human":[46],"labeling.To":[47],"address":[48],"these":[49],"limitations,":[50],"this":[51],"study":[52],"conducts":[53],"empirical":[54],"experiments":[55],"unlabeled":[57],"corpora,":[59],"varying":[60],"both":[61,121],"the":[62],"number":[63],"proportion":[65],"combinations":[68],"to":[69,142],"identify":[70],"effective":[71],"mixtures.To":[72],"minimize":[73],"manual":[74],"labeling,":[75],"we":[76,100],"automatically":[77],"extract":[78],"five":[79],"representative":[80],"tasks-programming,":[81],"math":[82],"problem":[83],"solving,":[84],"history":[85],"question":[86],"answering,":[87],"grammar":[88],"correction,":[89],"creative":[91,132],"writing-using":[92],"only":[93],"few":[95],"seed":[96],"instructions.Across":[97],"51":[98],"mixtures,":[99],"find":[101],"that":[102],"1-2":[103],"mixtures":[105,114],"work":[106],"best":[107],"with":[108,116],"small":[109],"datasets,":[110],"while":[111],"synergistic":[112],"3-task":[113],"excel":[115],"larger":[117],"data.Task":[118],"reveal":[120],"synergy":[122],"(e.g.,":[123,129],"programming":[124,130],"+":[125,131],"math)":[126],"interference":[128],"writing).These":[133],"results":[134],"provide":[135],"practical":[136],"guidelines":[137],"for":[138],"design":[140],"tailored":[141],"model":[143],"scale":[144],"data":[146],"size.":[147]},"counts_by_year":[],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2026-07-02T00:00:00"}