{"id":"https://openalex.org/W4412068610","doi":"https://doi.org/10.3390/computers14070264","title":"A Comprehensive Approach to Instruction Tuning for Qwen2.5: Data Selection, Domain Interaction, and Training Protocols","display_name":"A Comprehensive Approach to Instruction Tuning for Qwen2.5: Data Selection, Domain Interaction, and Training Protocols","publication_year":2025,"publication_date":"2025-07-05","ids":{"openalex":"https://openalex.org/W4412068610","doi":"https://doi.org/10.3390/computers14070264"},"language":"en","primary_location":{"id":"doi:10.3390/computers14070264","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14070264","pdf_url":"https://www.mdpi.com/2073-431X/14/7/264/pdf?version=1751864477","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-431X/14/7/264/pdf?version=1751864477","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013557235","display_name":"Xungang Gu","orcid":"https://orcid.org/0000-0003-1454-9304"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xungang Gu","raw_affiliation_strings":["School of Information Technology, Deakin University, Melbourne, VIC 3125, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1454-9304","affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Melbourne, VIC 3125, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100603095","display_name":"Mengqi Wang","orcid":"https://orcid.org/0000-0003-3167-0464"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mengqi Wang","raw_affiliation_strings":["School of Information Technology, Deakin University, Melbourne, VIC 3125, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Melbourne, VIC 3125, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000997942","display_name":"Yangjie Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangjie Tian","raw_affiliation_strings":["Kexin Technology, Beijing 100012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kexin Technology, Beijing 100012, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369062","display_name":"Ning Li","orcid":"https://orcid.org/0000-0002-8906-4849"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Li","raw_affiliation_strings":["Kexin Technology, Beijing 100012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kexin Technology, Beijing 100012, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061298622","display_name":"Jiaze Sun","orcid":"https://orcid.org/0000-0001-6610-8653"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaze Sun","raw_affiliation_strings":["Kexin Technology, Beijing 100012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kexin Technology, Beijing 100012, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102861619","display_name":"Jingfang Xu","orcid":"https://orcid.org/0000-0003-3699-7116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingfang Xu","raw_affiliation_strings":["Kexin Technology, Beijing 100012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kexin Technology, Beijing 100012, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115076705","display_name":"He Zhang","orcid":"https://orcid.org/0000-0003-2812-2192"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"He Zhang","raw_affiliation_strings":["Kexin Technology, Beijing 100012, China"],"raw_orcid":"https://orcid.org/0000-0003-2812-2192","affiliations":[{"raw_affiliation_string":"Kexin Technology, Beijing 100012, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057783064","display_name":"Ruohua Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruohua Xu","raw_affiliation_strings":["Kexin Technology, Beijing 100012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kexin Technology, Beijing 100012, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100347785","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0002-4500-238X"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ming Liu","raw_affiliation_strings":["School of Information Technology, Deakin University, Melbourne, VIC 3125, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Melbourne, VIC 3125, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100347785","https://openalex.org/A5115076705"],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":1.4278,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86319323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"14","issue":"7","first_page":"264","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.36480000615119934,"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":0.36480000615119934,"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/computer-science","display_name":"Computer science","score":0.707361102104187},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6493645310401917},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6131564378738403},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5453304052352905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37411272525787354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3510746657848358},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05876576900482178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707361102104187},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6493645310401917},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6131564378738403},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5453304052352905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37411272525787354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3510746657848358},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05876576900482178},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/computers14070264","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14070264","pdf_url":"https://www.mdpi.com/2073-431X/14/7/264/pdf?version=1751864477","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9ff3dd5bfb014d97b4b4a4871060225f","is_oa":true,"landing_page_url":"https://doaj.org/article/9ff3dd5bfb014d97b4b4a4871060225f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers, Vol 14, Iss 7, p 264 (2025)","raw_type":"article"},{"id":"pmh:oai:figshare.com:article/29848862","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Journal contribution"}],"best_oa_location":{"id":"doi:10.3390/computers14070264","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14070264","pdf_url":"https://www.mdpi.com/2073-431X/14/7/264/pdf?version=1751864477","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412068610.pdf","grobid_xml":"https://content.openalex.org/works/W4412068610.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W4319653585","https://openalex.org/W4377297670","https://openalex.org/W4380136143","https://openalex.org/W4385570724","https://openalex.org/W4385889714","https://openalex.org/W4401042981","https://openalex.org/W4402667025","https://openalex.org/W4402671025","https://openalex.org/W4404782653","https://openalex.org/W6852449896","https://openalex.org/W6853775986"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Instruction":[0],"tuning":[1],"plays":[2],"a":[3,80,125,150],"pivotal":[4],"role":[5],"in":[6,124],"aligning":[7],"large":[8],"language":[9],"models":[10],"with":[11],"diverse":[12],"tasks,":[13],"yet":[14],"its":[15],"effectiveness":[16],"hinges":[17],"on":[18,43],"the":[19,58,146],"interplay":[20],"of":[21,76],"data":[22,44,46,92],"quality,":[23],"domain":[24,119],"composition,":[25],"and":[26,48,85,105,140],"training":[27,49,107,112],"strategies.":[28],"This":[29],"study":[30],"moves":[31],"beyond":[32],"qualitative":[33],"assessment":[34],"to":[35,152,156],"systematically":[36],"quantify":[37],"these":[38,98],"factors":[39],"through":[40],"extensive":[41],"experiments":[42],"selection,":[45],"mixture,":[47],"protocols.":[50],"By":[51],"quantifying":[52],"performance":[53,139],"trade-offs,":[54],"we":[55,101],"demonstrate":[56],"that":[57,89,110],"implicit":[59],"method":[60],"SuperFiltering":[61],"achieves":[62],"an":[63],"optimal":[64],"balance,":[65],"whereas":[66],"explicit":[67],"filters":[68],"can":[69],"induce":[70],"capability":[71],"conflicts.":[72],"A":[73],"fine-grained":[74],"analysis":[75],"cross-domain":[77],"interactions":[78],"quantifies":[79],"near-linear":[81],"competition":[82],"between":[83],"code":[84],"math,":[86],"while":[87,117],"showing":[88],"tool":[90],"use":[91],"exhibits":[93],"minimal":[94],"interference.":[95],"To":[96],"mitigate":[97],"measured":[99],"conflicts,":[100],"compare":[102],"multi-task,":[103],"sequential,":[104],"multi-stage":[106,111],"strategies,":[108],"revealing":[109],"significantly":[113],"reduces":[114],"Conflict":[115],"Rates":[116],"preserving":[118],"expertise.":[120],"Our":[121],"findings":[122],"culminate":[123],"unified":[126],"framework":[127],"for":[128,136],"optimizing":[129],"instruction":[130],"tuning,":[131],"offering":[132],"actionable,":[133],"data-driven":[134],"guidelines":[135],"balancing":[137],"multi-domain":[138],"enhancing":[141],"model":[142],"generalization,":[143],"thus":[144],"advancing":[145],"field":[147],"by":[148],"providing":[149],"methodology":[151],"move":[153],"from":[154],"intuition":[155],"systematic":[157],"optimization.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
