{"id":"https://openalex.org/W4414359227","doi":"https://doi.org/10.24963/ijcai.2025/928","title":"D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning","display_name":"D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359227","doi":"https://doi.org/10.24963/ijcai.2025/928"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/928","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/928","pdf_url":"https://www.ijcai.org/proceedings/2025/0928.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0928.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071973450","display_name":"Jia Zhang","orcid":"https://orcid.org/0000-0002-0107-7152"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jia Zhang","raw_affiliation_strings":["Algorithm Tech, Taobao & Tmall Group of Alibaba","National Key Laboratory for Novel Software Technology, Nanjing University","School of Artificial Intelligence, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Algorithm Tech, Taobao & Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361491","display_name":"Chenxi Zhang","orcid":"https://orcid.org/0000-0002-8940-0902"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chen-Xi Zhang","raw_affiliation_strings":["Algorithm Tech, Taobao & Tmall Group of Alibaba","National Key Laboratory for Novel Software Technology, Nanjing University","School of Artificial Intelligence, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Algorithm Tech, Taobao & Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620900","display_name":"Yao Liu","orcid":"https://orcid.org/0000-0003-2783-3291"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao Liu","raw_affiliation_strings":["Algorithm Tech, Taobao & Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Algorithm Tech, Taobao & Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yi-Xuan Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi-Xuan Jin","raw_affiliation_strings":["Algorithm Tech, Taobao & Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Algorithm Tech, Taobao & Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101118190","display_name":"Xiaowen Yang","orcid":"https://orcid.org/0000-0003-0955-4977"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Wen Yang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University","School of Artificial Intelligence, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022979237","display_name":"Bo Zheng","orcid":"https://orcid.org/0000-0001-9172-9478"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Zheng","raw_affiliation_strings":["Algorithm Tech, Taobao & Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Algorithm Tech, Taobao & Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330461","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0001-8680-0508"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Algorithm Tech, Taobao & Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Algorithm Tech, Taobao & Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047808444","display_name":"Lan-Zhe Guo","orcid":"https://orcid.org/0000-0001-8965-1288"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan-Zhe Guo","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University","School of Intelligence Science and Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology, Nanjing University","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3141,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92903206,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8348","last_page":"8356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9524000287055969,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9524000287055969,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9006999731063843,"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/redundancy","display_name":"Redundancy (engineering)","score":0.5160999894142151},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4772999882698059},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.42579999566078186},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4178999960422516},{"id":"https://openalex.org/keywords/optimal-distinctiveness-theory","display_name":"Optimal distinctiveness theory","score":0.4050999879837036},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.37279999256134033},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3684999942779541},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.36579999327659607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925999760627747},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5756000280380249},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.477400004863739},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.42579999566078186},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4171999990940094},{"id":"https://openalex.org/C47385372","wikidata":"https://www.wikidata.org/wiki/Q7098943","display_name":"Optimal distinctiveness theory","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C77019957","wikidata":"https://www.wikidata.org/wiki/Q2689057","display_name":"Dependability","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C131806220","wikidata":"https://www.wikidata.org/wiki/Q852705","display_name":"Evaluation function","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C65660741","wikidata":"https://www.wikidata.org/wiki/Q3952743","display_name":"Score","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/928","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/928","pdf_url":"https://www.ijcai.org/proceedings/2025/0928.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2025/928","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/928","pdf_url":"https://www.ijcai.org/proceedings/2025/0928.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414359227.pdf","grobid_xml":"https://content.openalex.org/works/W4414359227.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,37,91,190],"instruction":[3,53],"tuning":[4],"for":[5,128,152],"large":[6,24,43],"language":[7],"models":[8],"(LLMs)":[9],"suggest":[10],"that":[11],"a":[12],"small,":[13],"high-quality":[14],"dataset":[15],"can":[16,162],"significantly":[17],"equip":[18],"LLMs":[19,192],"with":[20,193],"instruction-following":[21,198],"capabilities,":[22],"outperforming":[23],"datasets":[25,44,178],"often":[26],"burdened":[27],"by":[28,114],"quality":[29],"and":[30,50,74,76,88,104,179],"redundancy":[31],"issues.":[32],"However,":[33],"the":[34,48,79,92,97,106,116,132,137,153,170,180,186,205],"challenge":[35],"lies":[36],"automatically":[38],"identifying":[39],"valuable":[40,155],"subsets":[41],"from":[42],"to":[45,100,110,150,168],"boost":[46],"both":[47,176],"effectiveness":[49,187],"efficiency":[51],"of":[52,69,86,118,147,160,188,204],"tuning.":[54],"In":[55,131],"this":[56],"paper,":[57],"we":[58,95,123,135],"first":[59],"establish":[60],"data":[61,70,148],"selection":[62,133,171],"criteria":[63],"based":[64],"on":[65,175],"three":[66,145],"distinct":[67],"aspects":[68,146],"value:":[71],"diversity,":[72],"difficulty,":[73],"dependability,":[75],"then":[77],"propose":[78],"D3":[80,138,161,189],"method":[81],"comprising":[82],"two":[83,158],"key":[84],"steps":[85,159],"scoring":[87,93],"selection.":[89],"Specifically,":[90],"step,":[94,134],"define":[96],"diversity":[98],"function":[99],"measure":[101],"sample":[102,112],"distinctiveness":[103],"introduce":[105],"uncertainty-based":[107],"prediction":[108],"difficulty":[109,113],"evaluate":[111],"mitigating":[115],"interference":[117],"context-oriented":[119],"generation":[120],"diversity.":[121],"Additionally,":[122],"integrate":[124],"an":[125],"external":[126],"LLM":[127],"dependability":[129],"assessment.":[130],"formulate":[136],"weighted":[139],"coreset":[140],"objective,":[141],"which":[142],"jointly":[143],"optimizes":[144],"value":[149],"solve":[151],"most":[154],"subset.":[156],"The":[157],"iterate":[163],"multiple":[164],"rounds,":[165],"incorporating":[166],"feedback":[167],"refine":[169],"focus":[172],"adaptively.":[173],"Experiments":[174],"public":[177],"real-world":[181],"Taobao":[182],"Live":[183],"application":[184],"demonstrate":[185],"endowing":[191],"competitive":[194],"or":[195],"even":[196],"superior":[197],"capabilities":[199],"using":[200],"less":[201],"than":[202],"10%":[203],"entire":[206],"dataset.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}