Diagnosing AI Explanation Methods with Folk Concepts of Behavior

We investigate a formalism for the conditions of a successful explanation of AI. We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. Theory of mind literature discusses the folk concept...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-11
Hauptverfasser: Jacovi, Alon, Bastings, Jasmijn, Gehrmann, Sebastian, Goldberg, Yoav, Filippova, Katja
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Jacovi, Alon
Bastings, Jasmijn
Gehrmann, Sebastian
Goldberg, Yoav
Filippova, Katja
description We investigate a formalism for the conditions of a successful explanation of AI. We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. Theory of mind literature discusses the folk concepts that humans use to understand and generalize behavior. We posit that folk concepts of behavior provide us with a "language" that humans understand behavior with. We use these folk concepts as a framework of social attribution by the human explainee - the information constructs that humans are likely to comprehend from explanations - by introducing a blueprint for an explanatory narrative (Figure 1) that explains AI behavior with these constructs. We then demonstrate that many XAI methods today can be mapped to folk concepts of behavior in a qualitative evaluation. This allows us to uncover their failure modes that prevent current methods from explaining successfully - i.e., the information constructs that are missing for any given XAI method, and whose inclusion can decrease the likelihood of misunderstanding AI behavior.
doi_str_mv 10.48550/arxiv.2201.11239
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2201_11239</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2623498150</sourcerecordid><originalsourceid>FETCH-LOGICAL-a959-7808dab54a7d907d78371f7a29910ff114278ea133ad7b1d27b3f155ce884b373</originalsourceid><addsrcrecordid>eNotj0FPwjAYhhsTEwnyAzzZxPOw39eVtjcRQUkwXrgv31jHirjOdSD8exE8vZcnb56HsTsQw9QoJR6pPfj9EFHAEAClvWI9lBISkyLesEGMGyEEjjQqJXvs6cXTug7R12s-nvPpodlSTZ0PNX93XRWKyH98V_FZ2H7ySahXrukiDyV_dhXtfWhv2XVJ2-gG_9tny9l0OXlLFh-v88l4kZBVNtFGmIJylZIurNCFNlJDqQmtBVGWAClq4wikpELnUKDOZQlKrZwxaS617LP7y-05L2ta_0XtMfvLzM6ZJ-LhQjRt-N652GWbsGvrk1OGI5SpNaCE_AUxzVOG</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2623498150</pqid></control><display><type>article</type><title>Diagnosing AI Explanation Methods with Folk Concepts of Behavior</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Jacovi, Alon ; Bastings, Jasmijn ; Gehrmann, Sebastian ; Goldberg, Yoav ; Filippova, Katja</creator><creatorcontrib>Jacovi, Alon ; Bastings, Jasmijn ; Gehrmann, Sebastian ; Goldberg, Yoav ; Filippova, Katja</creatorcontrib><description>We investigate a formalism for the conditions of a successful explanation of AI. We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. Theory of mind literature discusses the folk concepts that humans use to understand and generalize behavior. We posit that folk concepts of behavior provide us with a "language" that humans understand behavior with. We use these folk concepts as a framework of social attribution by the human explainee - the information constructs that humans are likely to comprehend from explanations - by introducing a blueprint for an explanatory narrative (Figure 1) that explains AI behavior with these constructs. We then demonstrate that many XAI methods today can be mapped to folk concepts of behavior in a qualitative evaluation. This allows us to uncover their failure modes that prevent current methods from explaining successfully - i.e., the information constructs that are missing for any given XAI method, and whose inclusion can decrease the likelihood of misunderstanding AI behavior.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2201.11239</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Communication ; Computer Science - Artificial Intelligence ; Failure modes</subject><ispartof>arXiv.org, 2023-11</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,781,882,27906</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2201.11239$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1613/jair.1.14053$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Jacovi, Alon</creatorcontrib><creatorcontrib>Bastings, Jasmijn</creatorcontrib><creatorcontrib>Gehrmann, Sebastian</creatorcontrib><creatorcontrib>Goldberg, Yoav</creatorcontrib><creatorcontrib>Filippova, Katja</creatorcontrib><title>Diagnosing AI Explanation Methods with Folk Concepts of Behavior</title><title>arXiv.org</title><description>We investigate a formalism for the conditions of a successful explanation of AI. We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. Theory of mind literature discusses the folk concepts that humans use to understand and generalize behavior. We posit that folk concepts of behavior provide us with a "language" that humans understand behavior with. We use these folk concepts as a framework of social attribution by the human explainee - the information constructs that humans are likely to comprehend from explanations - by introducing a blueprint for an explanatory narrative (Figure 1) that explains AI behavior with these constructs. We then demonstrate that many XAI methods today can be mapped to folk concepts of behavior in a qualitative evaluation. This allows us to uncover their failure modes that prevent current methods from explaining successfully - i.e., the information constructs that are missing for any given XAI method, and whose inclusion can decrease the likelihood of misunderstanding AI behavior.</description><subject>Communication</subject><subject>Computer Science - Artificial Intelligence</subject><subject>Failure modes</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj0FPwjAYhhsTEwnyAzzZxPOw39eVtjcRQUkwXrgv31jHirjOdSD8exE8vZcnb56HsTsQw9QoJR6pPfj9EFHAEAClvWI9lBISkyLesEGMGyEEjjQqJXvs6cXTug7R12s-nvPpodlSTZ0PNX93XRWKyH98V_FZ2H7ySahXrukiDyV_dhXtfWhv2XVJ2-gG_9tny9l0OXlLFh-v88l4kZBVNtFGmIJylZIurNCFNlJDqQmtBVGWAClq4wikpELnUKDOZQlKrZwxaS617LP7y-05L2ta_0XtMfvLzM6ZJ-LhQjRt-N652GWbsGvrk1OGI5SpNaCE_AUxzVOG</recordid><startdate>20231115</startdate><enddate>20231115</enddate><creator>Jacovi, Alon</creator><creator>Bastings, Jasmijn</creator><creator>Gehrmann, Sebastian</creator><creator>Goldberg, Yoav</creator><creator>Filippova, Katja</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20231115</creationdate><title>Diagnosing AI Explanation Methods with Folk Concepts of Behavior</title><author>Jacovi, Alon ; Bastings, Jasmijn ; Gehrmann, Sebastian ; Goldberg, Yoav ; Filippova, Katja</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a959-7808dab54a7d907d78371f7a29910ff114278ea133ad7b1d27b3f155ce884b373</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Communication</topic><topic>Computer Science - Artificial Intelligence</topic><topic>Failure modes</topic><toplevel>online_resources</toplevel><creatorcontrib>Jacovi, Alon</creatorcontrib><creatorcontrib>Bastings, Jasmijn</creatorcontrib><creatorcontrib>Gehrmann, Sebastian</creatorcontrib><creatorcontrib>Goldberg, Yoav</creatorcontrib><creatorcontrib>Filippova, Katja</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jacovi, Alon</au><au>Bastings, Jasmijn</au><au>Gehrmann, Sebastian</au><au>Goldberg, Yoav</au><au>Filippova, Katja</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Diagnosing AI Explanation Methods with Folk Concepts of Behavior</atitle><jtitle>arXiv.org</jtitle><date>2023-11-15</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>We investigate a formalism for the conditions of a successful explanation of AI. We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. Theory of mind literature discusses the folk concepts that humans use to understand and generalize behavior. We posit that folk concepts of behavior provide us with a "language" that humans understand behavior with. We use these folk concepts as a framework of social attribution by the human explainee - the information constructs that humans are likely to comprehend from explanations - by introducing a blueprint for an explanatory narrative (Figure 1) that explains AI behavior with these constructs. We then demonstrate that many XAI methods today can be mapped to folk concepts of behavior in a qualitative evaluation. This allows us to uncover their failure modes that prevent current methods from explaining successfully - i.e., the information constructs that are missing for any given XAI method, and whose inclusion can decrease the likelihood of misunderstanding AI behavior.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2201.11239</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-11
issn 2331-8422
language eng
recordid cdi_arxiv_primary_2201_11239
source arXiv.org; Free E- Journals
subjects Communication
Computer Science - Artificial Intelligence
Failure modes
title Diagnosing AI Explanation Methods with Folk Concepts of Behavior
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T07%3A24%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Diagnosing%20AI%20Explanation%20Methods%20with%20Folk%20Concepts%20of%20Behavior&rft.jtitle=arXiv.org&rft.au=Jacovi,%20Alon&rft.date=2023-11-15&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2201.11239&rft_dat=%3Cproquest_arxiv%3E2623498150%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2623498150&rft_id=info:pmid/&rfr_iscdi=true