{"id":"https://openalex.org/W7138965469","doi":"https://doi.org/10.1609/aaai.v40i41.40786","title":"Token-Context Attention for NLI: An Alternative to Self-Attention","display_name":"Token-Context Attention for NLI: An Alternative to Self-Attention","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138965469","doi":"https://doi.org/10.1609/aaai.v40i41.40786"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i41.40786","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i41.40786","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40786/44747","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40786/44747","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100430876","display_name":"Xi Zhang","orcid":"https://orcid.org/0000-0003-3415-5345"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Texas Tech University"],"affiliations":[{"raw_affiliation_string":"Texas Tech University","institution_ids":["https://openalex.org/I12315562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130204899","display_name":"Victor S. Sheng","orcid":null},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor S. Sheng","raw_affiliation_strings":["Texas Tech University"],"affiliations":[{"raw_affiliation_string":"Texas Tech University","institution_ids":["https://openalex.org/I12315562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100430876"],"corresponding_institution_ids":["https://openalex.org/I12315562"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87320192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"41","first_page":"34836","last_page":"34844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5148000121116638,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5148000121116638,"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/T10028","display_name":"Topic Modeling","score":0.17069999873638153,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.04820000007748604,"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/security-token","display_name":"Security token","score":0.8014000058174133},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6845999956130981},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6464999914169312},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6194000244140625},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5615000128746033},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5138000249862671},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5098000168800354},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4018999934196472}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8014000058174133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734000027179718},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6845999956130981},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6464999914169312},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5615000128746033},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5138000249862671},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5098000168800354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4968000054359436},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.33980000019073486},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.323199987411499},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3068999946117401},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i41.40786","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i41.40786","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40786/44747","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i41.40786","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i41.40786","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40786/44747","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5757418870925903,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1353381076","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G1912064254","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4006316252","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4676224565","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4968279142","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G509285653","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5173294414","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G682994450","display_name":"Category II: REPACSS: Empowering Scientific Discovery through Renewable Energy Powered Advanced Computing Systems and Services","funder_award_id":"2404438","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7622549653","display_name":null,"funder_award_id":"213829","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8165146668","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G8300691027","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8819975937","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138965469.pdf","grobid_xml":"https://content.openalex.org/works/W7138965469.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,73,120],"rapid":[2],"progress":[3],"in":[4,47,133],"large":[5],"language":[6,19],"models":[7,33],"(LLMs),":[8],"even":[9],"sub-billion-scale":[10],"systems":[11],"perform":[12],"at":[13],"chance":[14],"level":[15],"on":[16,72,124],"challenging":[17],"natural":[18],"inference":[20],"(NLI)":[21],"benchmarks":[22],"such":[23],"as":[24],"Adversarial":[25],"Natural":[26],"Language":[27],"Inference":[28],"(ANLI),":[29],"while":[30,128],"training":[31],"larger":[32],"is":[34],"often":[35],"impractical":[36],"due":[37],"to":[38,151],"limited":[39],"computational":[40],"resources.":[41],"We":[42],"address":[43],"this":[44],"parameter-efficiency":[45],"bottleneck":[46],"NLI":[48,155],"with":[49],"a":[50,63,80,148],"Complex-Vector":[51],"Token":[52],"Representation":[53],"that":[54,67,141],"explicitly":[55,142],"decouples":[56],"each":[57,69],"token":[58,70,144],"from":[59],"its":[60],"context,":[61],"and":[62,95,112,118,126,145],"Token-Context":[64,82],"Attention":[65,83],"mechanism":[66],"updates":[68],"based":[71],"most":[74],"informative":[75],"contextual":[76],"semantics.":[77],"On":[78],"ANLI,":[79],"0.8B-parameter":[81],"model":[84],"achieves":[85,119],"higher":[86],"parameter":[87],"efficiency":[88],"(accuracy":[89],"per":[90],"parameter)":[91],"than":[92],"all":[93],"1B":[94],"comparable":[96],"0.8B":[97],"self-attention":[98,153],"baselines;":[99],"it":[100],"also":[101],"suffers":[102],"smaller":[103],"performance":[104],"degradation":[105,132],"under":[106],"Fast":[107],"Gradient":[108,114],"Sign":[109],"Method":[110],"(FGSM)":[111],"Projected":[113],"Descent":[115],"(PGD)":[116],"attacks":[117],"largest":[121],"few-shot":[122],"gains":[123],"SNLI":[125],"MNLI":[127],"exhibiting":[129],"no":[130],"significant":[131],"ANLI":[134],"accuracy":[135],"after":[136],"adaptation.":[137],"These":[138],"results":[139],"suggest":[140],"disentangling":[143],"context":[146],"offers":[147],"viable":[149],"alternative":[150],"standard":[152],"for":[154],"tasks.":[156]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-20T00:00:00"}