{"id":"https://openalex.org/W4412889719","doi":"https://doi.org/10.18653/v1/2025.acl-long.1493","title":"A Survey on Efficient Large Language Model Training: From Data-centric Perspectives","display_name":"A Survey on Efficient Large Language Model Training: From Data-centric Perspectives","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889719","doi":"https://doi.org/10.18653/v1/2025.acl-long.1493"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1493","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1493","pdf_url":"https://aclanthology.org/2025.acl-long.1493.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1493.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101912906","display_name":"Junyu Luo","orcid":"https://orcid.org/0009-0001-6894-1144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyu Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101494739","display_name":"Bohan Wu","orcid":"https://orcid.org/0000-0003-0588-459X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bohan Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426938","display_name":"Xiao Luo","orcid":"https://orcid.org/0000-0002-7987-3714"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102016849","display_name":"Zhiping Xiao","orcid":"https://orcid.org/0000-0002-3165-6163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiping Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yiqiao Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiqiao Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012821978","display_name":"Rong-Cheng Tu","orcid":"https://orcid.org/0000-0002-9621-450X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong-Cheng Tu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027852193","display_name":"Nan Yin","orcid":"https://orcid.org/0000-0002-0177-8514"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398568","display_name":"Yifan Wang","orcid":"https://orcid.org/0000-0003-4742-1657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113747152","display_name":"Jingyang Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyang Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018666299","display_name":"Wei Ju","orcid":"https://orcid.org/0000-0001-9657-951X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Ju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100447218","display_name":"Ming Zhang","orcid":"https://orcid.org/0000-0001-6967-1732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6921,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96978133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"30904","last_page":"30920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9873999953269958,"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":0.9873999953269958,"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":0.9825999736785889,"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":0.7625269889831543},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6484935283660889},{"id":"https://openalex.org/keywords/database-centric-architecture","display_name":"Database-centric architecture","score":0.47157496213912964},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.44781211018562317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33628806471824646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3201131224632263},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.23195692896842957},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22009286284446716},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.07308125495910645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7625269889831543},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6484935283660889},{"id":"https://openalex.org/C154240960","wikidata":"https://www.wikidata.org/wiki/Q2860294","display_name":"Database-centric architecture","level":5,"score":0.47157496213912964},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.44781211018562317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33628806471824646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3201131224632263},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.23195692896842957},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22009286284446716},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.07308125495910645},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C35869016","wikidata":"https://www.wikidata.org/wiki/Q846636","display_name":"Software architecture","level":3,"score":0.0},{"id":"https://openalex.org/C41065761","wikidata":"https://www.wikidata.org/wiki/Q2193309","display_name":"Applications architecture","level":4,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1493","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1493","pdf_url":"https://aclanthology.org/2025.acl-long.1493.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.25817","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.25817","pdf_url":"https://arxiv.org/pdf/2510.25817","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1493","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1493","pdf_url":"https://aclanthology.org/2025.acl-long.1493.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1504557152","display_name":null,"funder_award_id":"2023YFC3341203","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2997987028","display_name":null,"funder_award_id":"62276002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889719.pdf","grobid_xml":"https://content.openalex.org/works/W4412889719.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4412817058","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Junyu":[0],"Luo,":[1,5],"Bohan":[2],"Wu,":[3],"Xiao":[4],"Zhiping":[6],"Xiao,":[7],"Yiqiao":[8],"Jin,":[9],"Rong-Cheng":[10],"Tu,":[11],"Nan":[12],"Yin,":[13],"Yifan":[14],"Wang,":[15],"Jingyang":[16],"Yuan,":[17],"Wei":[18],"Ju,":[19],"Ming":[20],"Zhang.":[21],"Proceedings":[22],"of":[23,28],"the":[24,29],"63rd":[25],"Annual":[26],"Meeting":[27],"Association":[30],"for":[31],"Computational":[32],"Linguistics":[33],"(Volume":[34],"1:":[35],"Long":[36],"Papers).":[37],"2025.":[38]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
