{"id":"https://openalex.org/W4380086373","doi":"https://doi.org/10.1017/s1351324923000268","title":"A resampling-based method to evaluate NLI models","display_name":"A resampling-based method to evaluate NLI models","publication_year":2023,"publication_date":"2023-06-09","ids":{"openalex":"https://openalex.org/W4380086373","doi":"https://doi.org/10.1017/s1351324923000268"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324923000268","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000268","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/36425029D22D619BF9ADB1FEF910D047/S1351324923000268a.pdf/div-class-title-a-resampling-based-method-to-evaluate-nli-models-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/36425029D22D619BF9ADB1FEF910D047/S1351324923000268a.pdf/div-class-title-a-resampling-based-method-to-evaluate-nli-models-div.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079291629","display_name":"Felipe Salvatore","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Felipe de Souza Salvatore","raw_affiliation_strings":["Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024395125","display_name":"Marcelo Finger","orcid":"https://orcid.org/0000-0002-1391-1175"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcelo Finger","raw_affiliation_strings":["Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006191190","display_name":"Roberto Hirata","orcid":"https://orcid.org/0000-0003-3861-7260"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Roberto Hirata","raw_affiliation_strings":["Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065337294","display_name":"Alexandre G. Patriota","orcid":"https://orcid.org/0000-0003-1327-3473"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alexandre G. Patriota","raw_affiliation_strings":["Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Matem\u00e1tica e Estat\u00edstica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079291629"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":0.3255,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63416638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"30","issue":"4","first_page":"793","last_page":"820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9986000061035156,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9818999767303467,"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":0.8603255748748779},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.778207540512085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6306369304656982},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.6044803261756897},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5845433473587036},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5734129548072815},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5530704259872437},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5442417860031128},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5102834701538086},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47835391759872437},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.41635602712631226},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10004246234893799}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8603255748748779},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.778207540512085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6306369304656982},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.6044803261756897},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5845433473587036},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5734129548072815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5530704259872437},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5442417860031128},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5102834701538086},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47835391759872437},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.41635602712631226},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10004246234893799},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s1351324923000268","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000268","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/36425029D22D619BF9ADB1FEF910D047/S1351324923000268a.pdf/div-class-title-a-resampling-based-method-to-evaluate-nli-models-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:003143650","is_oa":true,"landing_page_url":"https://doi.org/10.1017/S1351324923000268","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"instacron:USP","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1017/s1351324923000268","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324923000268","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/36425029D22D619BF9ADB1FEF910D047/S1351324923000268a.pdf/div-class-title-a-resampling-based-method-to-evaluate-nli-models-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1139104289","display_name":null,"funder_award_id":"2014/12236-1","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G2045583916","display_name":null,"funder_award_id":"2018/21934-5","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G2313742006","display_name":null,"funder_award_id":"2015/24485-9","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G295657101","display_name":null,"funder_award_id":"2019/","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G3215658456","display_name":null,"funder_award_id":"2018-4","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G3572101131","display_name":null,"funder_award_id":"2014/","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G3794326933","display_name":null,"funder_award_id":"Code 001","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G4113406716","display_name":null,"funder_award_id":"2015/22308","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G4312984384","display_name":null,"funder_award_id":"2014/12236-1","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G4402799499","display_name":null,"funder_award_id":"2015/","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G5088577386","display_name":null,"funder_award_id":"2019/07665-4","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G5132839547","display_name":null,"funder_award_id":"2015/21880-4","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G5360564821","display_name":null,"funder_award_id":"2015/22308-2","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G5555641840","display_name":null,"funder_award_id":"2018/21934-5","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G5612035544","display_name":null,"funder_award_id":"2015/22308-2","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G5658673143","display_name":null,"funder_award_id":"2019/07665-4","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G6713122265","display_name":null,"funder_award_id":"2019/07665-4","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G674745710","display_name":null,"funder_award_id":"PQ 303609/2018-4","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G7106066699","display_name":null,"funder_award_id":"2015/22308-2","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G7285438780","display_name":null,"funder_award_id":"2014/12236-1","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G8369302488","display_name":null,"funder_award_id":"2018/21934-5","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"}],"funders":[{"id":"https://openalex.org/F4320307762","display_name":"International Business Machines Corporation","ror":"https://ror.org/05hh8d621"},{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4380086373.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1840435438","https://openalex.org/W2054779505","https://openalex.org/W2084413241","https://openalex.org/W2087600499","https://openalex.org/W2097998348","https://openalex.org/W2140879899","https://openalex.org/W2157134953","https://openalex.org/W2163332530","https://openalex.org/W2798665661","https://openalex.org/W2798819017","https://openalex.org/W2805083708","https://openalex.org/W2888643140","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2927622107","https://openalex.org/W2943552823","https://openalex.org/W2951286828","https://openalex.org/W2962736243","https://openalex.org/W2963026768","https://openalex.org/W2963372062","https://openalex.org/W2963542100","https://openalex.org/W2963846996","https://openalex.org/W2965373594","https://openalex.org/W2970442950","https://openalex.org/W2971089712","https://openalex.org/W2975059944","https://openalex.org/W2980282514","https://openalex.org/W2984978596","https://openalex.org/W2997789497","https://openalex.org/W2999905431","https://openalex.org/W3033187248","https://openalex.org/W3034850762","https://openalex.org/W3127191965","https://openalex.org/W3167252906","https://openalex.org/W3171654528","https://openalex.org/W3175508917","https://openalex.org/W3211686893","https://openalex.org/W3212567773","https://openalex.org/W4235505822","https://openalex.org/W4287867774","https://openalex.org/W4288089799","https://openalex.org/W6674385629","https://openalex.org/W6681303651","https://openalex.org/W6734424637","https://openalex.org/W6748164123","https://openalex.org/W6756488962","https://openalex.org/W6762392948","https://openalex.org/W6768817161","https://openalex.org/W6769627184","https://openalex.org/W6773642575","https://openalex.org/W6796401879","https://openalex.org/W6803557570"],"related_works":["https://openalex.org/W4379255972","https://openalex.org/W4383955378","https://openalex.org/W4295850094","https://openalex.org/W2974723675","https://openalex.org/W3201070945","https://openalex.org/W2896317853","https://openalex.org/W4289367650","https://openalex.org/W2912441862","https://openalex.org/W3090337104","https://openalex.org/W2888706357"],"abstract_inverted_index":{"Abstract":[0],"The":[1,94,155,197],"recent":[2],"progress":[3],"of":[4,12,28,35,194],"deep":[5],"learning":[6,111],"techniques":[7],"has":[8],"produced":[9],"models":[10,187,207],"capable":[11],"achieving":[13],"high":[14,203],"scores":[15],"on":[16,56,70,84,116,170],"traditional":[17],"Natural":[18],"Language":[19],"Inference":[20],"(NLI)":[21],"datasets.":[22,173],"To":[23,138],"understand":[24],"the":[25,79,85,122,127,135,148,167,180,184,192,229],"generalization":[26],"limits":[27],"these":[29,206],"powerful":[30],"models,":[31],"an":[32],"increasing":[33],"number":[34],"adversarial":[36,65,86,128,163,195,226],"evaluation":[37,46,98,146],"schemes":[38],"have":[39],"appeared.":[40],"These":[41],"works":[42],"use":[43],"a":[44,50,68,71,91,106,117,144,159,175],"similar":[45],"method:":[47],"they":[48],"construct":[49],"new":[51,80,118,145],"NLI":[52,73,186],"test":[53,119,152,157,182],"set":[54,87,120,129],"based":[55],"sentences":[57],"with":[58,96,161],"known":[59],"logic":[60],"and":[61,75,165],"semantic":[62],"properties":[63],"(the":[64],"set),":[66],"train":[67],"model":[69,92,112,160],"benchmark":[72],"dataset,":[74],"evaluate":[76],"it":[77,102],"in":[78,126,134,228],"set.":[81],"Poor":[82],"performance":[83,169],"is":[88,100],"identified":[89],"as":[90,191],"limitation.":[93],"problem":[95],"this":[97,140,219],"procedure":[99],"that":[101],"may":[103],"only":[104],"indicate":[105],"sampling":[107],"problem.":[108],"A":[109],"machine":[110],"can":[113],"perform":[114],"poorly":[115],"because":[121],"text":[123],"patterns":[124],"presented":[125],"are":[130],"not":[131],"well":[132],"represented":[133],"training":[136,230],"sample.":[137],"address":[139],"problem,":[141],"we":[142,178],"present":[143],"method,":[147],"Invariance":[149],"under":[150],"Equivalence":[151],"(IE":[153],"test).":[154],"IE":[156,181],"trains":[158],"sufficient":[162],"examples":[164],"checks":[166],"model\u2019s":[168],"two":[171],"equivalent":[172,214],"As":[174],"case":[176],"study,":[177],"apply":[179],"to":[183],"state-of-the-art":[185],"using":[188],"synonym":[189],"substitution":[190],"form":[193],"examples.":[196],"experiment":[198],"shows":[199],"that,":[200],"despite":[201],"their":[202],"predictive":[204],"power,":[205],"usually":[208],"produce":[209],"different":[210],"inference":[211],"outputs":[212],"for":[213],"inputs,":[215],"and,":[216],"more":[217],"importantly,":[218],"deficiency":[220],"cannot":[221],"be":[222],"solved":[223],"by":[224],"adding":[225],"observations":[227],"data.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2025-10-10T00:00:00"}