{"id":"https://openalex.org/W7103140566","doi":"https://doi.org/10.48550/arxiv.2510.25817","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":"2025-10-29","ids":{"openalex":"https://openalex.org/W7103140566","doi":"https://doi.org/10.48550/arxiv.2510.25817"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2510.25817","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.25817","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2510.25817","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Luo, Junyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Luo, Junyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, Bohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Bohan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Luo, Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao, Zhiping","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Zhiping","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jin, Yiqiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Yiqiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tu, Rong-Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Rong-Cheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yin, Nan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Nan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Yifan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yifan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuan, Jingyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Jingyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ju, Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zhang, Ming","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ming","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.35269999504089355,"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/T10028","display_name":"Topic Modeling","score":0.35269999504089355,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.10790000110864639,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.0851999968290329,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5139999985694885},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5102999806404114},{"id":"https://openalex.org/keywords/open-research","display_name":"Open research","score":0.45010000467300415},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.43950000405311584},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.439300000667572},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4090000092983246},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.39730000495910645},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.38449999690055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373999953269958},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5151000022888184},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5139999985694885},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41119998693466187},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2510.25817","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.25817","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2510.25817","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.25817","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Post-training":[0],"of":[1,31,60,72,134],"Large":[2],"Language":[3],"Models":[4],"(LLMs)":[5],"is":[6],"crucial":[7],"for":[8],"unlocking":[9],"their":[10],"task":[11],"generalization":[12],"potential":[13,120,133],"and":[14,34,88,90,101,118],"domain-specific":[15],"capabilities.":[16],"However,":[17],"the":[18,28,56,108,132],"current":[19],"LLM":[20,62,74,112],"post-training":[21,44,63,75],"paradigm":[22],"faces":[23],"significant":[24],"data":[25,39,78,80,84,86,92,135],"challenges,":[26],"including":[27],"high":[29],"costs":[30],"manual":[32],"annotation":[33],"diminishing":[35],"marginal":[36],"returns":[37],"on":[38],"scales.":[40],"Therefore,":[41],"achieving":[42],"data-efficient":[43,61,73,111],"has":[45],"become":[46],"a":[47,65,70],"key":[48],"research":[49,104,121],"question.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,114],"present":[55],"first":[57],"systematic":[58],"survey":[59],"from":[64],"data-centric":[66],"perspective.":[67],"We":[68,94,123],"propose":[69,119],"taxonomy":[71],"methods,":[76],"covering":[77],"selection,":[79],"quality":[81],"enhancement,":[82],"synthetic":[83],"generation,":[85],"distillation":[87],"compression,":[89],"self-evolving":[91],"ecosystems.":[93],"summarize":[95],"representative":[96],"approaches":[97],"in":[98,110,137],"each":[99],"category":[100],"outline":[102],"future":[103],"directions.":[105],"By":[106],"examining":[107],"challenges":[109],"post-training,":[113],"highlight":[115],"open":[116],"problems":[117],"avenues.":[122],"hope":[124],"our":[125],"work":[126],"inspires":[127],"further":[128],"exploration":[129],"into":[130],"maximizing":[131],"utilization":[136],"large-scale":[138],"model":[139],"training.":[140],"Paper":[141],"List:":[142],"https://github.com/luo-junyu/Awesome-Data-Efficient-LLM":[143]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-11-01T00:00:00"}