{"id":"https://openalex.org/W4411119989","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.264","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","display_name":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411119989","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.264"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-naacl.264","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.264","pdf_url":"https://aclanthology.org/2025.findings-naacl.264.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: NAACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-naacl.264.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100622777","display_name":"Jipeng Zhang","orcid":"https://orcid.org/0000-0001-9638-2741"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jipeng Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yaxuan Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yaxuan Qin","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084438237","display_name":"Renjie Pi","orcid":"https://orcid.org/0000-0002-5033-7096"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Renjie Pi","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693733","display_name":"Weizhong Zhang","orcid":"https://orcid.org/0000-0003-2164-6321"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhong Zhang","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638028","display_name":"Rui Pan","orcid":"https://orcid.org/0000-0002-9448-5752"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rui Pan","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378762","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0001-7659-5184"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7423,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96706851,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4671","last_page":"4686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.9776999950408936,"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":0.9776999950408936,"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"}},{"id":"https://openalex.org/T14025","display_name":"Educational Technology and Assessment","score":0.9503999948501587,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.932699978351593,"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/computer-science","display_name":"Computer science","score":0.7480748891830444},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.666863203048706},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6533258557319641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3074091970920563},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0506766140460968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480748891830444},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.666863203048706},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6533258557319641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3074091970920563},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0506766140460968},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-naacl.264","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.264","pdf_url":"https://aclanthology.org/2025.findings-naacl.264.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: NAACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-naacl.264","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.264","pdf_url":"https://aclanthology.org/2025.findings-naacl.264.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: NAACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411119989.pdf","grobid_xml":"https://content.openalex.org/works/W4411119989.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2389015757"],"abstract_inverted_index":{"Instruction":[0],"tuning":[1],"has":[2],"achieved":[3],"unprecedented":[4],"success":[5],"in":[6],"NLP,":[7],"turning":[8],"large":[9,87],"language":[10],"models":[11],"into":[12],"versatile":[13],"chatbots.However,":[14],"the":[15,47,64,70,79,82,105,132,145],"increasing":[16],"variety":[17],"and":[18,36,76,114,138],"volume":[19],"of":[20,73,81,131,144],"instruction":[21,74],"datasets":[22],"demand":[23],"significant":[24],"computational":[25],"resources.To":[26],"address":[27,89],"this,":[28],"it":[29],"is":[30],"essential":[31],"to":[32,46,110,142],"extract":[33],"a":[34],"small":[35],"highly":[37],"informative":[38],"subset":[39],"(i.e.,":[40],"Coreset)":[41],"that":[42,62,125,143],"achieves":[43,139],"comparable":[44],"performance":[45,140],"full":[48,146],"dataset.Achieving":[49],"this":[50],"goal":[51],"poses":[52],"nontrivial":[53],"challenges:":[54],"1)":[55],"data":[56,60,106],"selection":[57,84],"requires":[58],"accurate":[59],"representations":[61],"reflect":[63],"training":[65],"samples'":[66],"quality,":[67],"2)":[68],"considering":[69],"diverse":[71],"nature":[72],"datasets,":[75],"3)":[77],"ensuring":[78],"efficiency":[80],"coreset":[83,121],"algorithm":[85,119],"for":[86,120],"models.To":[88],"these":[90],"challenges,":[91],"we":[92,100],"propose":[93],"Task-Agnostic":[94],"Gradient":[95],"Clustered":[96],"COreset":[97],"Selection":[98],"(TAGCOS).Specifically,":[99],"leverage":[101],"sample":[102],"gradients":[103],"as":[104],"representations,":[107],"perform":[108],"clustering":[109],"group":[111],"similar":[112],"data,":[113,133],"apply":[115],"an":[116],"efficient":[117],"greedy":[118],"selection.Experimental":[122],"results":[123],"show":[124],"our":[126],"algorithm,":[127],"selecting":[128],"only":[129],"5%":[130],"surpasses":[134],"other":[135],"unsupervised":[136],"methods":[137],"close":[141],"dataset.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}