{"id":"https://openalex.org/W4415269742","doi":"https://doi.org/10.48550/arxiv.2510.12178","title":"Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey","display_name":"Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W4415269742","doi":"https://doi.org/10.48550/arxiv.2510.12178"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.12178","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.12178","pdf_url":"https://arxiv.org/pdf/2510.12178","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.12178","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038294530","display_name":"Abdulhady Abas Abdullah","orcid":"https://orcid.org/0009-0007-5508-9371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdullah, Abdulhady Abas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071220716","display_name":"Arkaitz Zubiaga","orcid":"https://orcid.org/0000-0003-4583-3623"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zubiaga, Arkaitz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091500375","display_name":"Seyedali Mirjalili","orcid":"https://orcid.org/0000-0002-1443-9458"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mirjalili, Seyedali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039341855","display_name":"Amir H. Gandomi","orcid":"https://orcid.org/0000-0002-2798-0104"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gandomi, Amir H.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003861036","display_name":"Fatemeh Daneshfar","orcid":"https://orcid.org/0000-0003-3150-3527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daneshfar, Fatemeh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Amini, Mohammadsadra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amini, Mohammadsadra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mohammed, Alan Salam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammed, Alan Salam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5035048262","display_name":"Hadi Veisi","orcid":"https://orcid.org/0000-0003-2372-7969"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Veisi, Hadi","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":null,"has_fulltext":true,"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":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8973000049591064,"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":0.8973000049591064,"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":0.8550000190734863,"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/key","display_name":"Key (lock)","score":0.4781999886035919},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4643000066280365},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4174000024795532},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3547999858856201},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.30140000581741333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6888999938964844},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4352000057697296},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36250001192092896},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.12178","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.12178","pdf_url":"https://arxiv.org/pdf/2510.12178","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.12178","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.12178","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.12178","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.12178","pdf_url":"https://arxiv.org/pdf/2510.12178","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415269742.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,185],"review":[1,82],"surveys":[2],"the":[3,24,37,64],"rapid":[4],"evolution":[5],"of":[6,40,66,79,127],"Meta":[7,13],"AI's":[8],"LLaMA":[9,18,21,38,115,141,199],"(Large":[10],"Language":[11],"Model":[12],"AI)":[14],"series":[15],"-":[16],"from":[17],"1":[19],"through":[20],"4":[22],"and":[23,52,55,62,81,97,100,111,125,129,134,155,163,166,171,182,195,201],"specialized":[25],"parameter-efficient":[26],"fine-tuning":[27,203],"(PEFT)":[28],"methods":[29,85],"developed":[30],"for":[31,192],"these":[32],"models.":[33],"We":[34,59,104,121],"first":[35],"describe":[36,61],"family":[39],"foundation":[41],"models":[42,72,142,154,200],"(7B-65B":[43],"to":[44,90,114,178],"288B":[45],"parameters),":[46],"their":[47],"architectures":[48],"(including":[49,137],"native":[50],"multimodal":[51,119],"Mixtureof-Experts":[53],"variants),":[54],"key":[56],"performance":[57],"characteristics.":[58],"then":[60],"discuss":[63,105,168],"concept":[65],"PEFT,":[67],"which":[68],"adapts":[69],"large":[70],"pre-trained":[71],"by":[73],"updating":[74],"only":[75],"a":[76,189],"small":[77],"subset":[78],"parameters,":[80],"five":[83],"PEFT":[84,156],"that":[86],"have":[87,157],"been":[88,158],"applied":[89,160],"LLaMA:":[91],"LoRA":[92],"(Low-Rank":[93],"Adaptation),":[94],"LLaMA-Adapter":[95],"V1":[96],"V2,":[98],"LLaMA-Excitor,":[99],"QLoRA":[101],"(Quantized":[102],"LoRA).":[103],"each":[106],"method's":[107],"mechanism,":[108],"parameter":[109,132],"savings,":[110],"example":[112],"application":[113],"(e.g.,":[116,161],"instruction":[117],"tuning,":[118],"tasks).":[120],"provide":[122],"structured":[123],"discussion":[124],"analysis":[126],"model":[128],"adapter":[130],"architectures,":[131],"counts,":[133],"benchmark":[135],"results":[136],"examples":[138],"where":[139,152],"fine-tuned":[140],"outperform":[143],"larger":[144,180],"baselines).":[145],"Finally,":[146],"we":[147,167],"examine":[148],"real-world":[149],"use":[150],"cases":[151],"LLaMA-based":[153],"successfully":[159],"legal":[162],"medical":[164],"domains),":[165],"ongoing":[169],"challenges":[170],"future":[172],"research":[173],"directions":[174],"(such":[175],"as":[176],"scaling":[177],"even":[179],"contexts":[181],"improving":[183],"robustness).":[184],"survey":[186],"paper":[187],"provides":[188],"one-stop":[190],"resource":[191],"ML":[193],"researchers":[194],"practitioners":[196],"interested":[197],"in":[198],"efficient":[202],"strategies.":[204]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-17T00:00:00"}