{"id":"https://openalex.org/W4396821993","doi":"https://doi.org/10.48550/arxiv.2405.05386","title":"Interpretability Needs a New Paradigm","display_name":"Interpretability Needs a New Paradigm","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4396821993","doi":"https://doi.org/10.48550/arxiv.2405.05386"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2405.05386","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.05386","pdf_url":"https://arxiv.org/pdf/2405.05386","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.05386","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Madsen, Andreas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Madsen, Andreas","raw_affiliation_strings":["Polytechnique Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015520086","display_name":"Himabindu Lakkaraju","orcid":"https://orcid.org/0000-0001-7922-6544","observed_orcids":["https://orcid.org/0000-0001-7922-6544"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lakkaraju, Himabindu","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102886212","display_name":"Siva Reddy","orcid":"https://orcid.org/0000-0003-3753-0323","observed_orcids":["https://orcid.org/0000-0003-3753-0323"]},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Reddy, Siva","raw_affiliation_strings":["Facebook CIFAR AI Chair","McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook CIFAR AI Chair","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027720969","display_name":"Sarath Chandar","orcid":"https://orcid.org/0000-0002-9678-2830","observed_orcids":["https://orcid.org/0000-0002-9678-2830"]},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chandar, Sarath","raw_affiliation_strings":["Canada CIFAR AI Chair","Polytechnique Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canada CIFAR AI Chair","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"Polytechnique Montr\u00e9al","institution_ids":["https://openalex.org/I45683168"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"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":1.0,"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":0.0,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/model-interpretability","display_name":"model interpretability","score":0.777999997138977},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.699999988079071},{"id":"https://openalex.org/keywords/post-hoc-explanation","display_name":"post-hoc explanation","score":0.9039999842643738},{"id":"https://openalex.org/keywords/black-box-modeling","display_name":"black-box models","score":0.7929999828338623},{"id":"https://openalex.org/keywords/paradigm-evolution","display_name":"paradigm evolution","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8470126390457153},{"id":"https://openalex.org/C43540301","wikidata":"https://www.wikidata.org/wiki/Q689971","display_name":"Paradigm shift","level":2,"score":0.598464846611023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39432212710380554},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.36070168018341064},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3406372666358948},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.324849009513855},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25238171219825745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24895888566970825},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12919548153877258},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10482850670814514}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2405.05386","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.05386","pdf_url":"https://arxiv.org/pdf/2405.05386","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.05386","doi":"https://doi.org/10.48550/arxiv.2405.05386","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.05386","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":"pmh:oai:arXiv.org:2405.05386","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.05386","pdf_url":"https://arxiv.org/pdf/2405.05386","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396821993.pdf","grobid_xml":"https://content.openalex.org/works/W4396821993.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1825675169","https://openalex.org/W1875666508","https://openalex.org/W2064675550","https://openalex.org/W2240067561","https://openalex.org/W2253993278","https://openalex.org/W2282821441","https://openalex.org/W2329768790","https://openalex.org/W2416885651","https://openalex.org/W2439568532","https://openalex.org/W2493343568","https://openalex.org/W2562979205","https://openalex.org/W2594475271","https://openalex.org/W2594633041","https://openalex.org/W2788199784","https://openalex.org/W2806219033","https://openalex.org/W2910705748","https://openalex.org/W2934842096","https://openalex.org/W2941681871","https://openalex.org/W2951286828","https://openalex.org/W2953337107","https://openalex.org/W2964204621","https://openalex.org/W2964303497","https://openalex.org/W2970862333","https://openalex.org/W2971048680","https://openalex.org/W2972059645","https://openalex.org/W2973193541","https://openalex.org/W2998991762","https://openalex.org/W3005086430","https://openalex.org/W3013891696","https://openalex.org/W3015575765","https://openalex.org/W3023935934","https://openalex.org/W3037116584","https://openalex.org/W3092292656","https://openalex.org/W3102385344","https://openalex.org/W3135773605","https://openalex.org/W3168975918","https://openalex.org/W3187467055","https://openalex.org/W3200059295","https://openalex.org/W3213645763","https://openalex.org/W4229494842","https://openalex.org/W4231799185","https://openalex.org/W4285148079","https://openalex.org/W4320812537","https://openalex.org/W4380136051","https://openalex.org/W4383215670","https://openalex.org/W4384648622","https://openalex.org/W4385327568","https://openalex.org/W4386566425","https://openalex.org/W4387561528","https://openalex.org/W4390604658","https://openalex.org/W4391709172","https://openalex.org/W4402671681","https://openalex.org/W7133198714","https://openalex.org/W7133228402"],"related_works":["https://openalex.org/W4404990778","https://openalex.org/W4398796384","https://openalex.org/W7108670114","https://openalex.org/W3087396445","https://openalex.org/W7108959318","https://openalex.org/W4205123268","https://openalex.org/W7204878658","https://openalex.org/W3155174240","https://openalex.org/W7206174903","https://openalex.org/W4285224640"],"abstract_inverted_index":{"Interpretability":[0],"is":[1,15,53,69,91],"the":[2,20,36,48,65,107,123,132],"study":[3],"of":[4,50,109],"explaining":[5],"models":[6,27,43,152,162,174],"in":[7,80,111],"understandable":[8],"terms":[9],"to":[10,29,64,77,172],"humans.":[11],"At":[12,47],"present,":[13],"interpretability":[14],"divided":[16],"into":[17],"two":[18],"paradigms:":[19],"intrinsic":[21],"paradigm,":[22,38],"which":[23,39,84],"believes":[24,40],"that":[25,41,92,115,154,164,175],"only":[26],"designed":[28],"be":[30,33,45,86,157],"explained":[31],"can":[32,44,85,127,156],"explained,":[34],"and":[35,136,180],"post-hoc":[37],"black-box":[42],"explained.":[46],"core":[49],"this":[51,140],"debate":[52],"how":[54],"each":[55],"paradigm":[56,150,170],"ensures":[57],"its":[58],"explanations":[59,75,165],"are":[60,117],"faithful,":[61],"i.e.,":[62],"true":[63],"model's":[66],"behavior.":[67],"This":[68,88],"important,":[70],"as":[71],"false":[72],"but":[73],"convincing":[74],"lead":[76],"unsupported":[78],"confidence":[79],"artificial":[81],"intelligence":[82],"(AI),":[83],"dangerous.":[87],"paper's":[89],"position":[90],"we":[93,113,126],"should":[94],"think":[95],"about":[96],"new":[97],"paradigms":[98,110,116,145],"while":[99],"staying":[100],"vigilant":[101],"regarding":[102],"faithfulness.":[103],"First,":[104],"by":[105,121],"examining":[106,122],"history":[108],"science,":[112],"see":[114],"constantly":[118],"evolving.":[119],"Then,":[120],"current":[124],"paradigms,":[125],"understand":[128],"their":[129,137],"underlying":[130],"beliefs,":[131],"value":[133],"they":[134],"bring,":[135],"limitations.":[138],"Finally,":[139],"paper":[141],"presents":[142],"3":[143],"emerging":[144],"for":[146],"interpretability.":[147],"The":[148,168],"first":[149],"designs":[151],"such":[153,163],"faithfulness":[155],"easily":[158],"measured.":[159],"Another":[160],"optimizes":[161],"become":[166],"faithful.":[167],"last":[169],"proposes":[171],"develop":[173],"produce":[176],"both":[177],"a":[178],"prediction":[179],"an":[181],"explanation.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-05-11T00:00:00"}
