{"id":"https://openalex.org/W4412944711","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1201","title":"Pruning General Large Language Models into Customized Expert Models","display_name":"Pruning General Large Language Models into Customized Expert Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944711","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1201"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1201","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1201","pdf_url":"https://aclanthology.org/2025.findings-acl.1201.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1201.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028772518","display_name":"Yiran Zhao","orcid":"https://orcid.org/0000-0001-7047-4146"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiran Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648428","display_name":"Guizhen Chen","orcid":"https://orcid.org/0009-0004-5270-2730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guizhen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003184366","display_name":"Kenji Kawaguchi","orcid":"https://orcid.org/0000-0002-5361-9793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenji Kawaguchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086674741","display_name":"Lidong Bing","orcid":"https://orcid.org/0000-0003-4565-6313"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lidong Bing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078121505","display_name":"Wenxuan Zhang","orcid":"https://orcid.org/0000-0003-0345-6380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxuan 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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15177638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23377","last_page":"23391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7978000044822693,"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":0.7978000044822693,"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":0.7282999753952026,"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/computer-science","display_name":"Computer science","score":0.7732198238372803},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7053283452987671},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6667985916137695},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.538057267665863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5348400473594666},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40522852540016174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7732198238372803},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7053283452987671},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6667985916137695},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.538057267665863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5348400473594666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40522852540016174},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1201","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1201","pdf_url":"https://aclanthology.org/2025.findings-acl.1201.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1201","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1201","pdf_url":"https://aclanthology.org/2025.findings-acl.1201.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1482925484","display_name":null,"funder_award_id":"Tier 1","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320324110","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944711.pdf","grobid_xml":"https://content.openalex.org/works/W4412944711.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Large":[0],"language":[1,7],"models":[2,42,114,137],"(LLMs)":[3],"have":[4],"revolutionized":[5],"natural":[6],"processing,":[8],"yet":[9],"their":[10],"substantial":[11,16],"model":[12,86,140],"sizes":[13],"often":[14,38,59],"require":[15],"computational":[17],"resources.To":[18],"preserve":[19],"computing":[20],"resources":[21],"and":[22,100,104,132,142],"accelerate":[23],"inference":[24],"speed,":[25],"it":[26],"is":[27,94],"crucial":[28],"to":[29,44,69,81],"prune":[30,82],"redundant":[31],"parameters,":[32],"especially":[33],"for":[34],"experienced":[35],"users":[36],"who":[37],"need":[39],"compact":[40],"expert":[41,91,113,131],"tailored":[43],"specific":[45],"downstream":[46],"scenarios.However,":[47],"most":[48],"existing":[49],"pruning":[50,105],"methods":[51],"focus":[52],"on":[53],"preserving":[54],"the":[55,97],"model's":[56],"general":[57,85,133],"capabilities,":[58],"requiring":[60],"extensive":[61],"post-training":[62],"or":[63],"suffering":[64],"from":[65,138],"degraded":[66],"performance":[67],"due":[68],"coarse-grained":[70],"pruning.In":[71],"this":[72],"work,":[73],"we":[74],"design":[75],"a":[76,83,88],"Custom":[77],"Pruning":[78],"method":[79],"(Cus-Prun)":[80],"large":[84],"into":[87],"smaller":[89],"lightweight":[90],"model,":[92],"which":[93],"positioned":[95],"along":[96],"\"language\",":[98],"\"domain\"":[99],"\"task\"":[101],"dimensions.By":[102],"identifying":[103],"irrelevant":[106],"neurons":[107],"of":[108],"each":[109],"dimension,":[110],"Cus-Prun":[111,121],"creates":[112],"without":[115],"any":[116],"post-training.Our":[117],"experiments":[118],"demonstrate":[119],"that":[120],"consistently":[122],"outperforms":[123],"other":[124],"methods,":[125],"achieving":[126],"minimal":[127],"loss":[128],"in":[129],"both":[130],"capabilities":[134],"across":[135],"various":[136],"different":[139],"families":[141],"sizes.":[143],"1":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}