{"id":"https://openalex.org/W3001062618","doi":"https://doi.org/10.1145/3377325.3377498","title":"Proxy tasks and subjective measures can be misleading in evaluating explainable AI systems","display_name":"Proxy tasks and subjective measures can be misleading in evaluating explainable AI systems","publication_year":2020,"publication_date":"2020-03-04","ids":{"openalex":"https://openalex.org/W3001062618","doi":"https://doi.org/10.1145/3377325.3377498","mag":"3001062618"},"language":"en","primary_location":{"id":"doi:10.1145/3377325.3377498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377325.3377498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.08298","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zana Bu\u00e7inca","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zana Bu\u00e7inca","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Phoebe Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phoebe Lin","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Krzysztof Z. Gajos","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krzysztof Z. Gajos","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":null,"display_name":"Elena L. Glassman","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elena L. Glassman","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":15.0334,"has_fulltext":false,"cited_by_count":247,"citation_normalized_percentile":{"value":0.99201631,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"454","last_page":"464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9991000294685364,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9991000294685364,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12805","display_name":"Cognitive Science and Mapping","score":0.9672999978065491,"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/proxy","display_name":"Proxy (statistics)","score":0.6657999753952026},{"id":"https://openalex.org/keywords/sociotechnical-system","display_name":"Sociotechnical system","score":0.6330999732017517},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.49549999833106995},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4553999900817871},{"id":"https://openalex.org/keywords/intelligent-decision-support-system","display_name":"Intelligent decision support system","score":0.25839999318122864}],"concepts":[{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.6657999753952026},{"id":"https://openalex.org/C127627568","wikidata":"https://www.wikidata.org/wiki/Q1639361","display_name":"Sociotechnical system","level":2,"score":0.6330999732017517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5782999992370605},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4828000068664551},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4401000142097473},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26669999957084656},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26089999079704285},{"id":"https://openalex.org/C56397880","wikidata":"https://www.wikidata.org/wiki/Q6044094","display_name":"Intelligent decision support system","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3377325.3377498","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377325.3377498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.08298","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.08298","pdf_url":"https://arxiv.org/pdf/2001.08298","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"pmh:oai:dash.harvard.edu:1/37367251","is_oa":false,"landing_page_url":"https://nrs.harvard.edu/URN-3:HUL.INSTREPOS:37367251","pdf_url":null,"source":{"id":"https://openalex.org/S4306401540","display_name":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"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":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.08298","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.08298","pdf_url":"https://arxiv.org/pdf/2001.08298","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2010158189","https://openalex.org/W2020785866","https://openalex.org/W2051842656","https://openalex.org/W2053075547","https://openalex.org/W2068185353","https://openalex.org/W2080490561","https://openalex.org/W2092813663","https://openalex.org/W2103812576","https://openalex.org/W2130011931","https://openalex.org/W2136720336","https://openalex.org/W2150104072","https://openalex.org/W2282821441","https://openalex.org/W2305540842","https://openalex.org/W2327670610","https://openalex.org/W2367397349","https://openalex.org/W2551317447","https://openalex.org/W2591972220","https://openalex.org/W2895739182","https://openalex.org/W2901481055","https://openalex.org/W2901895173","https://openalex.org/W2902784621","https://openalex.org/W2916904544","https://openalex.org/W2918341242","https://openalex.org/W2942157335","https://openalex.org/W2942444880","https://openalex.org/W2953923985","https://openalex.org/W2962858109","https://openalex.org/W2963847595","https://openalex.org/W2971755171","https://openalex.org/W2979893369","https://openalex.org/W2984353433","https://openalex.org/W2997560917","https://openalex.org/W6773822957"],"related_works":[],"abstract_inverted_index":{"Explainable":[0],"artificially":[1],"intelligent":[2],"(XAI)":[3],"systems":[4,20],"form":[5],"part":[6],"of":[7,28,78,84,89,103],"sociotechnical":[8],"systems,":[9],"e.g.,":[10],"human+AI":[11,29,150],"teams":[12,30,151],"tasked":[13],"with":[14,95,106,117],"making":[15],"decisions.":[16],"Yet,":[17],"current":[18],"XAI":[19,53],"are":[21],"rarely":[22],"evaluated":[23],"by":[24,135],"measuring":[25],"the":[26,66,70,101,104,107,112,124],"performance":[27,126],"on":[31,115,127],"actual":[32,85,108,118],"decision-making":[33,109,119],"tasks.":[34,110,130],"We":[35],"conducted":[36],"two":[37,47],"online":[38],"experiments":[39,91],"and":[40,73,80],"one":[41],"in-person":[42],"think-aloud":[43],"study":[44],"to":[45],"evaluate":[46],"currently":[48],"common":[49],"techniques":[50],"for":[51],"evaluating":[52],"systems:":[54],"(1)":[55],"using":[56,75],"proxy,":[57],"artificial":[58],"tasks":[59,97,120],"such":[60],"as":[61,82],"how":[62],"well":[63],"humans":[64,158],"predict":[65,100,123],"AI's":[67],"decision":[68],"from":[69],"given":[71],"explanations,":[72],"(2)":[74],"subjective":[76,113],"measures":[77,114],"trust":[79],"preference":[81],"predictors":[83],"performance.":[86],"The":[87],"results":[88,102,132],"our":[90,140],"demonstrate":[92],"that":[93,134,152],"evaluations":[94,105,116],"proxy":[96],"did":[98,121],"not":[99,122],"Further,":[111],"objective":[125],"those":[128],"same":[129],"Our":[131],"suggest":[133],"employing":[136],"misleading":[137],"evaluation":[138],"methods,":[139],"field":[141],"may":[142],"be":[143],"inadvertently":[144],"slowing":[145],"its":[146],"progress":[147],"toward":[148],"developing":[149],"can":[153],"reliably":[154],"perform":[155],"better":[156],"than":[157],"or":[159],"AIs":[160],"alone.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":30},{"year":2025,"cited_by_count":53},{"year":2024,"cited_by_count":53},{"year":2023,"cited_by_count":47},{"year":2022,"cited_by_count":43},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2020-01-30T00:00:00"}
