{"id":"https://openalex.org/W4416257191","doi":"https://doi.org/10.1109/tnnls.2025.3628671","title":"Survey on Efficient Large Language Models: Principles, Algorithms, Applications, and Open Issues","display_name":"Survey on Efficient Large Language Models: Principles, Algorithms, Applications, and Open Issues","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416257191","doi":"https://doi.org/10.1109/tnnls.2025.3628671","pmid":"https://pubmed.ncbi.nlm.nih.gov/41237023"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3628671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3628671","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113012130","display_name":"Jian Cheng","orcid":"https://orcid.org/0000-0002-9805-8870"},"institutions":[{"id":"https://openalex.org/I4210165649","display_name":"China Coal Research Institute (China)","ror":"https://ror.org/05dy2c135","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210165649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cheng","raw_affiliation_strings":["Research Institute of Mine Artificial Intelligence, Chinese Institute of Coal Science, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9805-8870","affiliations":[{"raw_affiliation_string":"Research Institute of Mine Artificial Intelligence, Chinese Institute of Coal Science, Beijing, China","institution_ids":["https://openalex.org/I4210165649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041191758","display_name":"Haidong Kang","orcid":"https://orcid.org/0000-0001-8533-5704"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haidong Kang","raw_affiliation_strings":["College of Software, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0001-8533-5704","affiliations":[{"raw_affiliation_string":"College of Software, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062630507","display_name":"Yongbo Shao","orcid":"https://orcid.org/0000-0003-2385-2305"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Shao","raw_affiliation_strings":["College of Software, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Software, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341024","display_name":"Nan Li","orcid":"https://orcid.org/0000-0001-9065-7548"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Li","raw_affiliation_strings":["College of Software, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Software, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pengjun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengjun Chen","raw_affiliation_strings":["College of Software, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Software, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431163","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0001-9048-2979"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-9048-2979","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020630479","display_name":"Saiqin Long","orcid":"https://orcid.org/0000-0001-7119-8673"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Saiqin Long","raw_affiliation_strings":["College of Information Science and Technology, Jinan University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7119-8673","affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Jinan University, Guangzhou, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079763362","display_name":"Xiaochun Yang","orcid":"https://orcid.org/0000-0002-6184-4771"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochun Yang","raw_affiliation_strings":["College of Software, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-6184-4771","affiliations":[{"raw_affiliation_string":"College of Software, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068061222","display_name":"Lianbo Ma","orcid":"https://orcid.org/0000-0002-9969-211X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianbo Ma","raw_affiliation_strings":["College of Software, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-9969-211X","affiliations":[{"raw_affiliation_string":"College of Software, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.772,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.97908587,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"37","issue":"5","first_page":"2025","last_page":"2045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1720999926328659,"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":0.1720999926328659,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.11240000277757645,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.08709999918937683,"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/inference","display_name":"Inference","score":0.7648000121116638},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5533999800682068},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5516999959945679},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5393000245094299},{"id":"https://openalex.org/keywords/open-research","display_name":"Open research","score":0.3668000102043152},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.3165999948978424}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7648000121116638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7378000020980835},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6104999780654907},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5533999800682068},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5393000245094299},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.367900013923645},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3628671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3628671","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:41237023","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41237023","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2757366449","display_name":null,"funder_award_id":"2024-TD-ZD016-04","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3365535196","display_name":null,"funder_award_id":"52574193","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3603513928","display_name":null,"funder_award_id":"62472079","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7626354807","display_name":null,"funder_award_id":"2025-TD-ZY001","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W3000881061","https://openalex.org/W3017024317","https://openalex.org/W3030901202","https://openalex.org/W3100439847","https://openalex.org/W3131922516","https://openalex.org/W3151130473","https://openalex.org/W3159727696","https://openalex.org/W3169726339","https://openalex.org/W3170490008","https://openalex.org/W3173365702","https://openalex.org/W3180037928","https://openalex.org/W3189877953","https://openalex.org/W4280546523","https://openalex.org/W4312290555","https://openalex.org/W4312849330","https://openalex.org/W4312910119","https://openalex.org/W4312960790","https://openalex.org/W4366341968","https://openalex.org/W4379652941","https://openalex.org/W4385245566","https://openalex.org/W4385571011","https://openalex.org/W4385571831","https://openalex.org/W4385571944","https://openalex.org/W4385572016","https://openalex.org/W4385572090","https://openalex.org/W4385572868","https://openalex.org/W4385574133","https://openalex.org/W4386702673","https://openalex.org/W4386939484","https://openalex.org/W4387321091","https://openalex.org/W4387939340","https://openalex.org/W4388979610","https://openalex.org/W4389519530","https://openalex.org/W4389520139","https://openalex.org/W4389523983","https://openalex.org/W4389524052","https://openalex.org/W4389524384","https://openalex.org/W4389524555","https://openalex.org/W4391853495","https://openalex.org/W4392359953","https://openalex.org/W4393144919","https://openalex.org/W4393147201","https://openalex.org/W4393149524","https://openalex.org/W4393160586","https://openalex.org/W4401042408","https://openalex.org/W4401042410","https://openalex.org/W4401042530","https://openalex.org/W4401042997","https://openalex.org/W4401176373","https://openalex.org/W4402667003","https://openalex.org/W4402670692","https://openalex.org/W4402671081","https://openalex.org/W4404792838","https://openalex.org/W4404918643","https://openalex.org/W4407361695","https://openalex.org/W4411245047","https://openalex.org/W4411403346","https://openalex.org/W4412722490","https://openalex.org/W7133191579","https://openalex.org/W7133198810","https://openalex.org/W7133219248","https://openalex.org/W7133227460","https://openalex.org/W7133228637","https://openalex.org/W7133231369","https://openalex.org/W7133231983","https://openalex.org/W7133233472","https://openalex.org/W7133241318","https://openalex.org/W7133244816"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,114,149],"rapid":[2],"advancement":[3],"of":[4,25,38,64,116,138],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"in":[9,23,148],"both":[10],"academia":[11],"and":[12,17,28,81,94,110,119,131,141,145,162,167,172],"industry,":[13],"their":[14],"growing":[15],"size":[16],"complexity":[18],"have":[19],"introduced":[20],"significant":[21],"challenges":[22],"terms":[24],"computational":[26],"cost":[27],"deployment":[29],"efficiency.":[30],"To":[31],"address":[32],"these":[33,124],"issues,":[34],"a":[35,61,96],"wide":[36],"range":[37],"inference":[39,53,66,92],"optimization":[40,93],"techniques-including":[41],"but":[42],"not":[43],"limited":[44],"to":[45,50,158],"model":[46,56,128],"compression-have":[47],"been":[48],"proposed":[49],"accelerate":[51],"LLM":[52,65,117,174],"while":[54],"preserving":[55],"performance.":[57],"This":[58],"survey":[59,156],"provides":[60],"comprehensive":[62],"overview":[63],"acceleration":[67],"strategies,":[68],"analyzing":[69],"them":[70],"from":[71],"multiple":[72],"perspectives,":[73],"including":[74,103],"foundational":[75],"principles,":[76],"algorithmic":[77],"techniques,":[78],"real-world":[79],"applications,":[80],"open":[82],"research":[83],"challenges.":[84],"We":[85],"begin":[86],"by":[87],"introducing":[88],"core":[89],"concepts":[90],"underlying":[91],"propose":[95],"new":[97],"taxonomy":[98],"that":[99],"categorizes":[100],"existing":[101],"approaches,":[102],"quantization,":[104],"pruning,":[105],"distillation,":[106],"efficient":[107,139,173],"architectures,":[108],"compilation,":[109],"hardware-aware":[111],"methods.":[112],"Following":[113],"lifecycle":[115],"development":[118],"deployment,":[120],"we":[121,134],"examine":[122],"how":[123],"techniques":[125],"interact":[126],"with":[127,170],"training,":[129],"fine-tuning,":[130],"serving.":[132],"Furthermore,":[133],"highlight":[135],"key":[136],"applications":[137],"LLMs":[140],"discuss":[142],"emerging":[143],"trends":[144],"unresolved":[146],"issues":[147],"field.":[150],"By":[151],"synthesizing":[152],"recent":[153],"advances,":[154],"this":[155],"aims":[157],"provide":[159],"actionable":[160],"insights":[161],"practical":[163],"guidance":[164],"for":[165],"researchers":[166],"practitioners":[168],"working":[169],"scalable":[171],"systems.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":7}],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-11-14T00:00:00"}