{"id":"https://openalex.org/W4416251400","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229274","title":"ALM-KD: Adaptive Layer Mapping Knowledge Distillation for LLMs","display_name":"ALM-KD: Adaptive Layer Mapping Knowledge Distillation for LLMs","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251400","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229274"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5120403231","display_name":"Xu Baizhou","orcid":null},"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":true,"raw_author_name":"Xu Baizhou","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100783556","display_name":"Zhilin Yang","orcid":"https://orcid.org/0000-0002-4799-1492"},"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":"Yang Zhilin","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Niu Xin","orcid":null},"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":"Niu Xin","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050642628","display_name":"Zhaoning Zhang","orcid":"https://orcid.org/0000-0001-7518-1385"},"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":"Zhang Zhaoning","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063982534","display_name":"Huang Zheng","orcid":"https://orcid.org/0000-0002-7311-6552"},"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":"Huang Zheng","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120403232","display_name":"Qiao Linbo","orcid":null},"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":"Qiao Linbo","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120403233","display_name":"Qi Yafei","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Yafei","raw_affiliation_strings":["Central South University,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Central South University,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5120403231"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.30320000648498535,"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":0.30320000648498535,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10859999805688858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.07190000265836716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.6743999719619751},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6650999784469604},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6212000250816345},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5852000117301941},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5390999913215637},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5099999904632568},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4108000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283999919891357},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6743999719619751},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6650999784469604},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6212000250816345},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5852000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5594000220298767},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4763000011444092},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C2779937294","wikidata":"https://www.wikidata.org/wiki/Q5513666","display_name":"GLUE","level":2,"score":0.3125},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2759999930858612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2923014074","https://openalex.org/W2946417913","https://openalex.org/W2948947170","https://openalex.org/W2970454332","https://openalex.org/W3008219293","https://openalex.org/W3105966348","https://openalex.org/W3177378457","https://openalex.org/W4285202066","https://openalex.org/W4318464561","https://openalex.org/W4385570210","https://openalex.org/W4390490761"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"models":[1],"are":[2],"renowned":[3],"for":[4,22,31,107,161],"their":[5,72,95],"proficiency":[6],"in":[7,18],"computationally":[8],"demanding":[9],"NLP":[10],"tasks.":[11],"However,":[12],"we":[13],"have":[14],"identified":[15],"several":[16],"shortcomings":[17],"current":[19],"distillation":[20,68],"methods":[21],"transformer-based":[23],"Large":[24],"Language":[25],"Models":[26],"(LLMs),":[27],"including":[28],"the":[29,38,59,67,115,120,130],"disregard":[30],"layer":[32],"importance,":[33],"inappropriate":[34],"mapping":[35],"granularity,":[36],"and":[37,64,81,104,148,163],"omission":[39],"of":[40,79,129,132],"dimetsionality":[41],"compression.":[42],"We":[43],"propose":[44],"Adaptive":[45],"Layer":[46],"Mapping":[47],"Knowledge":[48],"Dis-tillation(ALM-KD),":[49],"a":[50],"method":[51],"designed":[52],"to":[53,88,94,97],"enhance":[54],"efficiency":[55],"by":[56,152],"adaptively":[57],"selecting":[58],"most":[60],"relevant":[61],"hidden":[62],"layers":[63,92],"dynamically":[65,89],"adjusting":[66],"weights":[69],"based":[70],"on":[71,114],"significance.":[73],"ALM-KD":[74,125,154],"utilizes":[75],"an":[76,85,140],"ada-learner":[77],"composed":[78],"RNN":[80],"MLP,":[82],"along":[83],"with":[84,139],"ada-loss":[86],"function,":[87],"prioritize":[90],"teacher":[91,134],"according":[93],"relevance":[96],"downstream":[98],"tasks,":[99],"while":[100],"also":[101],"integrating":[102],"horizontal":[103],"vertical":[105],"compression":[106,142],"substantial":[108],"model":[109,122],"knowledge":[110],"reduction.":[111],"Our":[112],"experiments":[113],"GLUE":[116],"benchmark":[117],"demonstrate":[118],"that":[119],"student":[121],"developed":[123],"using":[124],"achieves":[126],"over":[127],"96%":[128],"performance":[131],"its":[133],"model,":[135],"BERT<inf":[136],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[137],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">base</inf>,":[138],"80%":[141],"rate,":[143],"nearly":[144],"tripling":[145],"inference":[146],"speed,":[147],"reducing":[149],"memory":[150],"usage":[151],"half.":[153],"thus":[155],"renders":[156],"deep":[157],"neural":[158],"networks":[159],"viable":[160],"real-time":[162],"high-concurrency":[164],"applications.":[165]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-11-14T00:00:00"}