{"id":"https://openalex.org/W4392849927","doi":"https://doi.org/10.1145/3652599","title":"Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding","display_name":"Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding","publication_year":2024,"publication_date":"2024-03-15","ids":{"openalex":"https://openalex.org/W4392849927","doi":"https://doi.org/10.1145/3652599"},"language":"en","primary_location":{"id":"doi:10.1145/3652599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652599","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652599","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652599","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022058333","display_name":"Yunchang Zhu","orcid":"https://orcid.org/0000-0003-3766-0275"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunchang Zhu","raw_affiliation_strings":["CAS Key Laboratory of AI Security, Institute of Computing Technology, CAS; University of the Chinese Academy of Sciences, Beijing, China","University of the Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of AI Security, Institute of Computing Technology, CAS; University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004759804","display_name":"Liang Pang","orcid":"https://orcid.org/0000-0003-1161-8546"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Pang","raw_affiliation_strings":["CAS Key Laboratory of AI Security, Institute of Computing Technology, CAS, Beijing China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of AI Security, Institute of Computing Technology, CAS, Beijing China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020769742","display_name":"Kangxi Wu","orcid":"https://orcid.org/0009-0000-2904-2296"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangxi Wu","raw_affiliation_strings":["CAS Key Laboratory of AI Security, Institute of Computing Technology, CAS; University of the Chinese Academy of Sciences, Beijing, China","University of the Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of AI Security, Institute of Computing Technology, CAS; University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616866","display_name":"Yanyan Lan","orcid":"https://orcid.org/0000-0002-7811-3262"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Lan","raw_affiliation_strings":["Institute for AI Industry Research, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103007496","display_name":"Huawei Shen","orcid":"https://orcid.org/0000-0003-1204-4820"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huawei Shen","raw_affiliation_strings":["CAS Key Laboratory of AI Security, Institute of Computing Technology, CAS; University of the Chinese Academy of Sciences, Beijing, China","University of the Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of AI Security, Institute of Computing Technology, CAS; University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["CAS Key Laboratory of AI Security, Institute of Computing Technology, CAS; University of the Chinese Academy of Sciences, Beijing, China","University of the Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of AI Security, Institute of Computing Technology, CAS; University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022058333"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.0178,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78637614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"42","issue":"5","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.994700014591217,"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":0.412425696849823},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.36804696917533875},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.365295946598053},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.3520316481590271},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3459945023059845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.412425696849823},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36804696917533875},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.365295946598053},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.3520316481590271},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3459945023059845}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652599","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652599","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3652599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652599","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652599","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7277894242","display_name":null,"funder_award_id":"62276248, U21B2046","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7351175257","display_name":null,"funder_award_id":"2022YFB3103700, 2022YFB3103704","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G740642855","display_name":null,"funder_award_id":"U21B2046","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8394619546","display_name":null,"funder_award_id":"2023111","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G986537704","display_name":null,"funder_award_id":"62276248","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"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392849927.pdf","grobid_xml":"https://content.openalex.org/works/W4392849927.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W1516184288","https://openalex.org/W1517322531","https://openalex.org/W1583837637","https://openalex.org/W1904365287","https://openalex.org/W1964162497","https://openalex.org/W1992113527","https://openalex.org/W1994530392","https://openalex.org/W1999817920","https://openalex.org/W2040631151","https://openalex.org/W2072112759","https://openalex.org/W2138621090","https://openalex.org/W2141527331","https://openalex.org/W2155195660","https://openalex.org/W2159859920","https://openalex.org/W2286300105","https://openalex.org/W2559655401","https://openalex.org/W2612690371","https://openalex.org/W2739351760","https://openalex.org/W2889787757","https://openalex.org/W2899663614","https://openalex.org/W2913860539","https://openalex.org/W2914304175","https://openalex.org/W2962718483","https://openalex.org/W2962851801","https://openalex.org/W2963159735","https://openalex.org/W2963323070","https://openalex.org/W2963341956","https://openalex.org/W2963654130","https://openalex.org/W2963748441","https://openalex.org/W2963846996","https://openalex.org/W2964348592","https://openalex.org/W2965373594","https://openalex.org/W2978670439","https://openalex.org/W2979826702","https://openalex.org/W2981852735","https://openalex.org/W2988119488","https://openalex.org/W2997759614","https://openalex.org/W3001279689","https://openalex.org/W3002072934","https://openalex.org/W3015468748","https://openalex.org/W3035590471","https://openalex.org/W3035744524","https://openalex.org/W3096655658","https://openalex.org/W3099700870","https://openalex.org/W3102378333","https://openalex.org/W3104033643","https://openalex.org/W3124980712","https://openalex.org/W3152887675","https://openalex.org/W3156636935","https://openalex.org/W3156650996","https://openalex.org/W3174203100","https://openalex.org/W3175111331","https://openalex.org/W3175987672","https://openalex.org/W3197394194","https://openalex.org/W3198963570","https://openalex.org/W3210968241","https://openalex.org/W4205992724","https://openalex.org/W4212774754","https://openalex.org/W4232633635","https://openalex.org/W4284704885","https://openalex.org/W4285122897","https://openalex.org/W4287828539","https://openalex.org/W4288089799","https://openalex.org/W4288364646","https://openalex.org/W4293304858","https://openalex.org/W4301243929","https://openalex.org/W6682891771","https://openalex.org/W6727785063","https://openalex.org/W6755977528","https://openalex.org/W6764043288","https://openalex.org/W6774302960","https://openalex.org/W6775204245","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Current":[0],"natural":[1],"language":[2,215],"understanding":[3],"(NLU)":[4],"models":[5,216,223],"have":[6],"been":[7],"continuously":[8],"scaling":[9],"up,":[10],"both":[11],"in":[12,57],"terms":[13],"of":[14,109,156,167,171,184,195],"model":[15,96,114,187],"size":[16],"and":[17,23,53,83,100,174,217],"input":[18,24,58,102],"context,":[19],"introducing":[20],"more":[21],"hidden":[22,49],"neurons.":[25],"While":[26],"this":[27,88],"generally":[28],"improves":[29],"performance":[30],"on":[31,69,139,165,201,210],"average,":[32],"the":[33,54,63,95,107,126,134,168,172,178,181,185,192],"extra":[34],"neurons":[35,50,59,73,122],"do":[36],"not":[37],"yield":[38],"a":[39,113,141,148,153,162],"consistent":[40],"improvement":[41],"for":[42,152,222],"all":[43],"instances.":[44],"This":[45],"is":[46,160,188],"because":[47],"some":[48],"are":[51,123],"redundant,":[52],"noise":[55,103],"mixed":[56],"tends":[60],"to":[61,86],"distract":[62],"model.":[64,137],"Previous":[65],"work":[66],"mainly":[67],"focuses":[68],"extrinsically":[70],"reducing":[71],"low-utility":[72],"by":[74,104],"additional":[75],"post-":[76],"or":[77,227],"pre-processing,":[78],"such":[79,140],"as":[80],"network":[81],"pruning":[82],"context":[84],"selection,":[85],"avoid":[87],"problem.":[89],"Beyond":[90],"that,":[91],"can":[92,115],"we":[93,146],"make":[94],"reduce":[97],"redundant":[98],"parameters":[99,226],"suppress":[101],"intrinsically":[105],"enhancing":[106],"utility":[108],"each":[110],"neuron?":[111],"If":[112],"efficiently":[116],"utilize":[117],"neurons,":[118],"no":[119,131],"matter":[120],"which":[121],"ablated":[124,127,175],"(disabled),":[125],"submodel":[128],"should":[129],"perform":[130],"better":[132],"than":[133],"original":[135],"full":[136,173,186],"Based":[138],"comparison":[142],"principle":[143],"between":[144],"models,":[145,176],"propose":[147],"cross-model":[149],"comparative":[150,196],"loss":[151,159,164,183,197],"broad":[154],"range":[155],"tasks.":[157],"Comparative":[158],"essentially":[161],"ranking":[163],"top":[166],"task-specific":[169,182],"losses":[170],"with":[177,224],"expectation":[179],"that":[180],"minimal.":[189],"We":[190],"demonstrate":[191],"universal":[193],"effectiveness":[194],"through":[198],"extensive":[199],"experiments":[200],"14":[202],"datasets":[203],"from":[204],"three":[205],"distinct":[206],"NLU":[207],"tasks":[208],"based":[209],"five":[211],"widely":[212],"used":[213],"pre-trained":[214],"find":[218],"it":[219],"particularly":[220],"superior":[221],"few":[225],"long":[228],"input.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}