{"id":"https://openalex.org/W4385573323","doi":"https://doi.org/10.18653/v1/2022.findings-emnlp.538","title":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","display_name":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","alternate_titles":[],"publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385573323","doi":"https://doi.org/10.18653/v1/2022.findings-emnlp.538"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.findings-emnlp.538","doi":"https://doi.org/10.18653/v1/2022.findings-emnlp.538","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-emnlp.538","pdf_url":"https://aclanthology.org/2022.findings-emnlp.538.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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: EMNLP 2022","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4385573323"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.findings-emnlp.538.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023797825","display_name":"Yuxin Xiao","orcid":"https://orcid.org/0000-0001-7251-6557","observed_orcids":["https://orcid.org/0000-0001-7251-6557","https://orcid.org/0009-0002-3562-2427","https://orcid.org/0009-0003-9670-5506"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Yuxin Xiao","raw_affiliation_strings":["Massachusetts Institute of Technology,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086233510","display_name":"Paul Pu Liang","orcid":"https://orcid.org/0000-0001-7768-3610","observed_orcids":["https://orcid.org/0000-0001-7768-3610"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Paul Pu Liang","raw_affiliation_strings":["Carnegie Mellon University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016469734","display_name":"Umang Bhatt","orcid":"https://orcid.org/0000-0002-4611-1668","observed_orcids":["https://orcid.org/0000-0002-4611-1668"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Umang Bhatt","raw_affiliation_strings":["University of Cambridge,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073310637","display_name":"Willie Neiswanger","orcid":"https://orcid.org/0000-0002-9619-5572","observed_orcids":["https://orcid.org/0000-0002-9619-5572"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Willie Neiswanger","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756","observed_orcids":["https://orcid.org/0000-0002-3752-2756"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Ruslan Salakhutdinov","raw_affiliation_strings":["Carnegie Mellon University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081398601","display_name":"Louis\u2010Philippe Morency","orcid":"https://orcid.org/0000-0001-6376-7696","observed_orcids":["https://orcid.org/0000-0001-6376-7696"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Louis-Philippe Morency","raw_affiliation_strings":["Carnegie Mellon University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.1302,"has_fulltext":true,"cited_by_count":149,"citation_normalized_percentile":{"value":0.98375591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":86,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7273","last_page":"7284"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5429999828338623,"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":0.5429999828338623,"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":0.38089999556541443,"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":0.025200000032782555,"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/uncertainty-quantification","display_name":"uncertainty quantification","score":0.9860000014305115},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.9850000143051147},{"id":"https://openalex.org/keywords/calibration","display_name":"calibration","score":0.6600000262260437},{"id":"https://openalex.org/keywords/electra","display_name":"Electra","score":0.7710000276565552},{"id":"https://openalex.org/keywords/focal-loss","display_name":"focal loss","score":0.9599999785423279},{"id":"https://openalex.org/keywords/domain-shift","display_name":"domain shift","score":0.6679999828338623},{"id":"https://openalex.org/keywords/classification","display_name":"classification","score":0.5479999780654907},{"id":"https://openalex.org/keywords/model-size","display_name":"model size","score":0.5730000138282776},{"id":"https://openalex.org/keywords/safety-critical-applications","display_name":"safety-critical applications","score":0.8309999704360962}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8303729891777039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7903714179992676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5373924970626831},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5317954421043396},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5251983404159546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5231279730796814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5073315501213074},{"id":"https://openalex.org/C2778523021","wikidata":"https://www.wikidata.org/wiki/Q5532504","display_name":"Quantifier (linguistics)","level":2,"score":0.4860556423664093},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4860230088233948},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4267466068267822},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4163011312484741},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.41443589329719543},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08181962370872498},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2022.findings-emnlp.538","doi":"https://doi.org/10.18653/v1/2022.findings-emnlp.538","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-emnlp.538","pdf_url":"https://aclanthology.org/2022.findings-emnlp.538.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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: EMNLP 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.04714","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.04714","pdf_url":"https://arxiv.org/pdf/2210.04714","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.04714","doi":"https://doi.org/10.48550/arxiv.2210.04714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.04714","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.findings-emnlp.538","doi":"https://doi.org/10.18653/v1/2022.findings-emnlp.538","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-emnlp.538","pdf_url":"https://aclanthology.org/2022.findings-emnlp.538.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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: EMNLP 2022","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4340203621","display_name":"CAREER: Learning Nonverbal Signatures","funder_award_id":"1750439","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G574185058","display_name":"SCH: INT: Collaborative Research: Dyadic Behavior Informatics for Psychotherapy Process and Outcome","funder_award_id":"1722822","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6078575908","display_name":"Automatic Multimodal Affect Detection for Research and Clinical Use\u00a0","funder_award_id":"R01MH096951","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"},{"id":"https://openalex.org/G6480834561","display_name":"Robust Predictors of Mania and Psychosis","funder_award_id":"U01MH116925","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"},{"id":"https://openalex.org/G8011784326","display_name":"SCH: INT: Collaborative Research: Context-Adaptive Multimodal Informatics for Psychiatric Discharge Planning","funder_award_id":"R01MH125740","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337346","display_name":"National Institute of Mental Health","ror":"https://ror.org/04xeg9z08"},{"id":"https://openalex.org/F4320337968","display_name":"Center for Machine Learning and Health, School of Computer Science, Carnegie Mellon University","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385573323.pdf","grobid_xml":"https://content.openalex.org/works/W4385573323.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W1826524928","https://openalex.org/W1840435438","https://openalex.org/W2061119986","https://openalex.org/W2073241381","https://openalex.org/W2113459411","https://openalex.org/W2137556846","https://openalex.org/W2158840489","https://openalex.org/W2164411961","https://openalex.org/W2170240176","https://openalex.org/W2560321925","https://openalex.org/W2600383743","https://openalex.org/W2607892599","https://openalex.org/W2622263826","https://openalex.org/W2626778328","https://openalex.org/W2626967530","https://openalex.org/W2788755844","https://openalex.org/W2790319220","https://openalex.org/W2799054028","https://openalex.org/W2804697534","https://openalex.org/W2810469995","https://openalex.org/W2886424491","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2923014074","https://openalex.org/W2948194985","https://openalex.org/W2950813464","https://openalex.org/W2963323070","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W2965373594","https://openalex.org/W2970206392","https://openalex.org/W2979826702","https://openalex.org/W2990704537","https://openalex.org/W2996035354","https://openalex.org/W2997090102","https://openalex.org/W2997604142","https://openalex.org/W3011574394","https://openalex.org/W3012209028","https://openalex.org/W3013838212","https://openalex.org/W3034201598","https://openalex.org/W3034408878","https://openalex.org/W3035154851","https://openalex.org/W3035782406","https://openalex.org/W3093891978","https://openalex.org/W3097606775","https://openalex.org/W3099796618","https://openalex.org/W3102100346","https://openalex.org/W3102315351","https://openalex.org/W3104448368","https://openalex.org/W3114632476","https://openalex.org/W3122890974","https://openalex.org/W3128453519","https://openalex.org/W3132800470","https://openalex.org/W3132954326","https://openalex.org/W3169554260","https://openalex.org/W3170360335","https://openalex.org/W3173618889","https://openalex.org/W3183398589","https://openalex.org/W3195430298","https://openalex.org/W3204348602","https://openalex.org/W3211561698","https://openalex.org/W3213215942","https://openalex.org/W4200630791","https://openalex.org/W4239966440","https://openalex.org/W4285146641","https://openalex.org/W4285298351","https://openalex.org/W4287023290","https://openalex.org/W4287865413","https://openalex.org/W4320341979","https://openalex.org/W4382246105","https://openalex.org/W6931468106","https://openalex.org/W7225208346"],"related_works":["https://openalex.org/W4385571092","https://openalex.org/W4386566509","https://openalex.org/W7134281628","https://openalex.org/W4385572118","https://openalex.org/W4415796703","https://openalex.org/W4285298706","https://openalex.org/W4378945695","https://openalex.org/W6929465362","https://openalex.org/W4402670050","https://openalex.org/W4414855266"],"abstract_inverted_index":{"Pre-trained":[0],"language":[1,17],"models":[2],"(PLMs)":[3],"have":[4],"gained":[5],"increasing":[6],"popularity":[7],"due":[8],"to":[9,36,117],"their":[10],"compelling":[11],"prediction":[12,24,122],"performance":[13],"in":[14,42],"diverse":[15],"natural":[16],"processing":[18],"(NLP)":[19],"tasks.When":[20],"formulating":[21],"a":[22,104,112,119,129],"PLM-based":[23,121],"pipeline":[25,35,47],"for":[26,33,135,159,181],"NLP":[27,142],"tasks,":[28],"it":[29],"is":[30],"also":[31],"crucial":[32],"the":[34,38,46,63,66,70,75,81,146,154,173],"minimize":[37],"calibration":[39],"error,":[40],"especially":[41],"safety-critical":[43],"applications.That":[44],"is,":[45],"should":[48],"reliably":[49],"indicate":[50],"when":[51],"we":[52,127,152],"can":[53],"trust":[54],"its":[55],"predictions.In":[56],"particular,":[57],"there":[58],"are":[59],"various":[60],"considerations":[61],"behind":[62],"pipeline:":[64],"(1)":[65,156],"choice":[67,76,82],"and":[68,86,145,176],"(2)":[69,162],"size":[71],"of":[72,77,83,95,107,132,148],"PLM,":[73],"(3)":[74,168],"uncertainty":[78,174],"quantifier,":[79,175],"(4)":[80,177],"fine-tuning":[84],"loss,":[85],"many":[87],"more.Although":[88],"prior":[89],"work":[90],"has":[91],"looked":[92],"into":[93],"some":[94],"these":[96],"considerations,":[97],"they":[98],"usually":[99],"draw":[100],"conclusions":[101],"based":[102,138],"on":[103,115,139],"limited":[105],"scope":[106],"empirical":[108],"studies.There":[109],"still":[110],"lacks":[111],"holistic":[113],"analysis":[114],"how":[116],"compose":[118],"wellcalibrated":[120],"pipeline.To":[123],"fill":[124],"this":[125],"void,":[126],"compare":[128],"wide":[130],"range":[131],"popular":[133],"options":[134],"each":[136],"consideration":[137],"three":[140],"prevalent":[141],"classification":[143],"tasks":[144],"setting":[147],"domain":[149],"shift.In":[150],"response,":[151],"recommend":[153],"following:":[155],"use":[157,163,169,178],"ELECTRA":[158],"PLM":[160],"encoding,":[161],"larger":[164],"PLMs":[165],"if":[166],"possible,":[167],"Temp":[170],"Scaling":[171],"as":[172],"Focal":[179],"Loss":[180],"fine-tuning.":[182]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4385573323","counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":60},{"year":2024,"cited_by_count":47},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-20T13:11:24.684918","created_date":"2023-08-05T00:00:00"}
