{"id":"https://openalex.org/W4416034703","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.688","title":"LimaCost: Data Valuation for Instruction Tuning of Large Language Models","display_name":"LimaCost: Data Valuation for Instruction Tuning of Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034703","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.688"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.688","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.688","pdf_url":"https://aclanthology.org/2025.findings-emnlp.688.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: EMNLP 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-emnlp.688.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048597650","display_name":"Hyeonseok Moon","orcid":"https://orcid.org/0000-0002-0841-4262"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Hyeonseok Moon","raw_affiliation_strings":["Department of Computer Science and Engineering , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014883878","display_name":"Jaehyung Seo","orcid":"https://orcid.org/0000-0002-4761-9818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaehyung Seo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078410336","display_name":"Seonmin Koo","orcid":"https://orcid.org/0009-0007-8575-2306"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Seonmin Koo","raw_affiliation_strings":["Department of Computer Science and Engineering , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676202","display_name":"Jinsung Kim","orcid":"https://orcid.org/0000-0002-1587-0389"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Jinsung Kim","raw_affiliation_strings":["Department of Computer Science and Engineering , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308662","display_name":"Young-kyoung Ham","orcid":null},"institutions":[{"id":"https://openalex.org/I101155339","display_name":"Korea Telecom (South Korea)","ror":"https://ror.org/043n4tt17","country_code":"KR","type":"company","lineage":["https://openalex.org/I101155339"]},{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Young-kyoung Ham","raw_affiliation_strings":["Department of Computer Science and Engineering , Korea University","Korea Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"]},{"raw_affiliation_string":"Korea Telecom","institution_ids":["https://openalex.org/I101155339"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101033798","display_name":"Jiwon Moon","orcid":"https://orcid.org/0009-0003-1863-4220"},"institutions":[{"id":"https://openalex.org/I101155339","display_name":"Korea Telecom (South Korea)","ror":"https://ror.org/043n4tt17","country_code":"KR","type":"company","lineage":["https://openalex.org/I101155339"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiwon Moon","raw_affiliation_strings":["Korea Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Telecom","institution_ids":["https://openalex.org/I101155339"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033580486","display_name":"Heuiseok Lim","orcid":"https://orcid.org/0000-0002-9269-1157"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Heuiseok Lim","raw_affiliation_strings":["Department of Computer Science and Engineering , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.28894544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12841","last_page":"12854"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.20200000703334808,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.20200000703334808,"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":0.16500000655651093,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06800000369548798,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/language-model","display_name":"Language model","score":0.36660000681877136},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.31119999289512634},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.30379998683929443},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2930000126361847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819999814033508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4413999915122986},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3167000114917755},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C186027771","wikidata":"https://www.wikidata.org/wiki/Q4008379","display_name":"Valuation (finance)","level":2,"score":0.23659999668598175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.688","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.688","pdf_url":"https://aclanthology.org/2025.findings-emnlp.688.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.688","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.688","pdf_url":"https://aclanthology.org/2025.findings-emnlp.688.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6181273566","display_name":null,"funder_award_id":"NRF-2021R1A6A1A03045425","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320332128","display_name":"Commercializations Promotion Agency for R and D Outcomes","ror":null},{"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/W4416034703.pdf","grobid_xml":"https://content.openalex.org/works/W4416034703.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Instruction":[0],"tuning":[1],"(IT)":[2],"is":[3,16],"an":[4,25],"effective":[5,94,114],"approach":[6],"for":[7,23,35],"aligning":[8],"large":[9],"language":[10],"models":[11],"(LLMs)":[12],"with":[13,49],"human":[14],"intentions.There":[15],"ongoing":[17],"discourse":[18],"regarding":[19],"the":[20,29,69],"data":[21,33,41,74,80,95,105,117],"quality":[22,34,42],"IT.As":[24],"effort":[26],"to":[27,85,111],"find":[28],"robust":[30],"criteria":[31],"of":[32,71],"IT,":[36],"we":[37],"introduce":[38],"LIMACOST,":[39],"a":[40,46,72],"measure":[43],"that":[44,91,97,103],"exhibits":[45],"strong":[47],"correlation":[48],"model":[50],"performance.LIMACOST":[51],"utilizes":[52],"LIMA":[53,79],"dataset,":[54],"which":[55],"effectiveness":[56],"in":[57],"IT":[58],"has":[59],"already":[60],"been":[61],"validated":[62],"by":[63,75],"several":[64],"previous":[65],"works.LI-MACOST":[66],"then":[67],"estimates":[68],"value":[70],"given":[73],"estimating":[76],"how":[77],"many":[78],"points":[81],"might":[82],"be":[83,112],"needed":[84],"approximate":[86],"its":[87],"gradient.Our":[88],"experiments":[89],"reveal":[90],"LIMACOST":[92,109],"enables":[93],"selection":[96,118],"derive":[98],"high":[99,108],"alignment":[100],"performance.We":[101],"demonstrate":[102],"selecting":[104],"based":[106],"on":[107],"proves":[110],"more":[113],"than":[115],"existing":[116],"strategies.":[119]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-11-08T00:00:00"}