{"id":"https://openalex.org/W4404918643","doi":"https://doi.org/10.1162/tacl_a_00704","title":"A Survey on Model Compression for Large Language Models","display_name":"A Survey on Model Compression for Large Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404918643","doi":"https://doi.org/10.1162/tacl_a_00704"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00704","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00704","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1162/tacl_a_00704","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065349324","display_name":"Xunyu Zhu","orcid":"https://orcid.org/0000-0001-9806-3445"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xunyu Zhu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China","School of Cyber Security, University of Chinese Academy of Sciences, China. zhuxunyu@iie.ac.cn"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, China. zhuxunyu@iie.ac.cn","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067173458","display_name":"Jian Li","orcid":"https://orcid.org/0000-0003-2614-4291"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Li","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, China. lijian9026@iie.ac.cn; jli@bnu.edu.cn"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, China. lijian9026@iie.ac.cn; jli@bnu.edu.cn","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032634769","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-0172-9867"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, China. liuyonggsai@ruc.edu.cn"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, China. liuyonggsai@ruc.edu.cn","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014152648","display_name":"Can Ma","orcid":"https://orcid.org/0000-0001-6174-8010"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Ma","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China","School of Cyber Security, University of Chinese Academy of Sciences, China. macan@iie.ac.cn"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, China. macan@iie.ac.cn","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115587803","display_name":"Weiping Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiping Wang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, China","School of Cyber Security, University of Chinese Academy of Sciences, China. wangweiping@iie.ac.cn"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, China. wangweiping@iie.ac.cn","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5065349324"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":49.2679,"has_fulltext":false,"cited_by_count":144,"citation_normalized_percentile":{"value":0.99905878,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"1556","last_page":"1577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9932000041007996,"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":0.9932000041007996,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9916999936103821,"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":0.9883000254631042,"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":0.8342699408531189},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4940100312232971},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4479243755340576},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.42196905612945557},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41812023520469666},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36000704765319824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3144901692867279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8342699408531189},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4940100312232971},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4479243755340576},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.42196905612945557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41812023520469666},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36000704765319824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3144901692867279},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1162/tacl_a_00704","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00704","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00704","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00704","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":132,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1632114991","https://openalex.org/W1674493795","https://openalex.org/W1821462560","https://openalex.org/W2002555321","https://openalex.org/W2300242332","https://openalex.org/W2559655401","https://openalex.org/W2753392522","https://openalex.org/W2890894339","https://openalex.org/W2963015836","https://openalex.org/W2963995027","https://openalex.org/W2965862774","https://openalex.org/W3001279689","https://openalex.org/W3104667152","https://openalex.org/W3118485687","https://openalex.org/W3130554079","https://openalex.org/W3159959439","https://openalex.org/W3197901717","https://openalex.org/W3198685994","https://openalex.org/W4212774754","https://openalex.org/W4229005866","https://openalex.org/W4254197176","https://openalex.org/W4281690148","https://openalex.org/W4286892945","https://openalex.org/W4288089799","https://openalex.org/W4307079201","https://openalex.org/W4311642023","https://openalex.org/W4312107430","https://openalex.org/W4318719086","https://openalex.org/W4322718191","https://openalex.org/W4324057834","https://openalex.org/W4327810129","https://openalex.org/W4362515116","https://openalex.org/W4362598949","https://openalex.org/W4366341968","https://openalex.org/W4367369802","https://openalex.org/W4379260375","https://openalex.org/W4380714727","https://openalex.org/W4384918448","https://openalex.org/W4385571011","https://openalex.org/W4385571219","https://openalex.org/W4385571260","https://openalex.org/W4385571831","https://openalex.org/W4385572016","https://openalex.org/W4385572634","https://openalex.org/W4386076215","https://openalex.org/W4387686975","https://openalex.org/W4387947524","https://openalex.org/W4388787967","https://openalex.org/W4389519530","https://openalex.org/W4389524052","https://openalex.org/W4389524393","https://openalex.org/W4389524481","https://openalex.org/W4389576338","https://openalex.org/W4389650671","https://openalex.org/W4391463154","https://openalex.org/W4391591383","https://openalex.org/W4391621451","https://openalex.org/W4391673374","https://openalex.org/W4392011959","https://openalex.org/W4392018977","https://openalex.org/W4392904185","https://openalex.org/W4393147284","https://openalex.org/W4393147854","https://openalex.org/W4393160586","https://openalex.org/W4401042410","https://openalex.org/W4402667003","https://openalex.org/W4402670692","https://openalex.org/W4402683727","https://openalex.org/W4404782964","https://openalex.org/W6638523607","https://openalex.org/W6677103964","https://openalex.org/W6684295950","https://openalex.org/W6725543821","https://openalex.org/W6727099177","https://openalex.org/W6729956949","https://openalex.org/W6736057607","https://openalex.org/W6751979845","https://openalex.org/W6757119728","https://openalex.org/W6769627184","https://openalex.org/W6772383348","https://openalex.org/W6778883912","https://openalex.org/W6796782416","https://openalex.org/W6803096969","https://openalex.org/W6809646742","https://openalex.org/W6810162553","https://openalex.org/W6810738896","https://openalex.org/W6811340617","https://openalex.org/W6838633097","https://openalex.org/W6839092155","https://openalex.org/W6839193947","https://openalex.org/W6842795023","https://openalex.org/W6846074030","https://openalex.org/W6846844205","https://openalex.org/W6847076894","https://openalex.org/W6847118041","https://openalex.org/W6847478871","https://openalex.org/W6847766160","https://openalex.org/W6848451824","https://openalex.org/W6848909144","https://openalex.org/W6849360995","https://openalex.org/W6850625674","https://openalex.org/W6851324747","https://openalex.org/W6851775633","https://openalex.org/W6851828392","https://openalex.org/W6852686595","https://openalex.org/W6852874933","https://openalex.org/W6852927819","https://openalex.org/W6852962002","https://openalex.org/W6853176743","https://openalex.org/W6853251322","https://openalex.org/W6853804809","https://openalex.org/W6854094408","https://openalex.org/W6854296101","https://openalex.org/W6854866820","https://openalex.org/W6855007554","https://openalex.org/W6856574389","https://openalex.org/W6856696905","https://openalex.org/W6857453862","https://openalex.org/W6857819823","https://openalex.org/W6857923988","https://openalex.org/W6857939981","https://openalex.org/W6858266299","https://openalex.org/W6860201728","https://openalex.org/W6860936625","https://openalex.org/W6860959834","https://openalex.org/W6861391505","https://openalex.org/W6861487172","https://openalex.org/W6861837763","https://openalex.org/W6862025885","https://openalex.org/W6862275039","https://openalex.org/W6893640197"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W2106335228","https://openalex.org/W2105076537","https://openalex.org/W2028371633","https://openalex.org/W2071315630","https://openalex.org/W2096375461","https://openalex.org/W4322096525","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"Abstract":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"have":[5],"transformed":[6],"natural":[7],"language":[8],"processing":[9],"tasks":[10],"successfully.":[11],"Yet,":[12],"their":[13],"large":[14],"size":[15],"and":[16,59,70,85,91],"high":[17],"computational":[18],"needs":[19],"pose":[20],"challenges":[21],"for":[22,51,74,83,100],"practical":[23],"use,":[24],"especially":[25],"in":[26],"resource-limited":[27],"settings.":[28],"Model":[29],"compression":[30,49],"has":[31],"emerged":[32],"as":[33],"a":[34,45,98],"key":[35],"research":[36],"area":[37],"to":[38,88],"address":[39],"these":[40],"challenges.":[41],"This":[42,78],"paper":[43],"presents":[44],"survey":[46,79],"of":[47,94],"model":[48],"techniques":[50],"LLMs.":[52,77],"We":[53,65],"cover":[54],"methods":[55],"like":[56],"quantization,":[57],"pruning,":[58],"knowledge":[60],"distillation,":[61],"highlighting":[62],"recent":[63],"advancements.":[64,102],"also":[66],"discuss":[67],"benchmarking":[68],"strategies":[69],"evaluation":[71],"metrics":[72],"crucial":[73],"assessing":[75],"compressed":[76],"offers":[80],"valuable":[81],"insights":[82],"researchers":[84],"practitioners,":[86],"aiming":[87],"enhance":[89],"efficiency":[90],"real-world":[92],"applicability":[93],"LLMs":[95],"while":[96],"laying":[97],"foundation":[99],"future":[101]},"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":107},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}