Measures for explainable AI: Explanation goodness, user satisfaction, mental models, curiosity, trust, and human-AI performance

If a user is presented an AI system that portends to explain how it works, how do we know whether the explanation works and the user has achieved a pragmatic understanding of the AI? This question entails some key concepts of measurement such as explanation goodness and trust. We present methods for...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in computer science (Lausanne) Vol. 5
Main Authors: Hoffman, Robert R., Mueller, Shane T., Klein, Gary, Litman, Jordan
Format: Journal Article
Language:English
Published: Frontiers Media S.A 06.02.2023
Subjects:
explanation goodness
explanatory reasoning
machine-generated explanations
measurement
mental models
trust
ISSN:2624-9898, 2624-9898
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract If a user is presented an AI system that portends to explain how it works, how do we know whether the explanation works and the user has achieved a pragmatic understanding of the AI? This question entails some key concepts of measurement such as explanation goodness and trust. We present methods for enabling developers and researchers to: (1) Assess the a priori goodness of explanations, (2) Assess users' satisfaction with explanations, (3) Reveal user's mental model of an AI system, (4) Assess user's curiosity or need for explanations, (5) Assess whether the user's trust and reliance on the AI are appropriate, and finally, (6) Assess how the human-XAI work system performs. The methods we present derive from our integration of extensive research literatures and our own psychometric evaluations. We point to the previous research that led to the measurement scales which we aggregated and tailored specifically for the XAI context. Scales are presented in sufficient detail to enable their use by XAI researchers. For Mental Model assessment and Work System Performance, XAI researchers have choices. We point to a number of methods, expressed in terms of methods' strengths and weaknesses, and pertinent measurement issues.
AbstractList If a user is presented an AI system that portends to explain how it works, how do we know whether the explanation works and the user has achieved a pragmatic understanding of the AI? This question entails some key concepts of measurement such as explanation goodness and trust. We present methods for enabling developers and researchers to: (1) Assess the a priori goodness of explanations, (2) Assess users' satisfaction with explanations, (3) Reveal user's mental model of an AI system, (4) Assess user's curiosity or need for explanations, (5) Assess whether the user's trust and reliance on the AI are appropriate, and finally, (6) Assess how the human-XAI work system performs. The methods we present derive from our integration of extensive research literatures and our own psychometric evaluations. We point to the previous research that led to the measurement scales which we aggregated and tailored specifically for the XAI context. Scales are presented in sufficient detail to enable their use by XAI researchers. For Mental Model assessment and Work System Performance, XAI researchers have choices. We point to a number of methods, expressed in terms of methods' strengths and weaknesses, and pertinent measurement issues.
If a user is presented an AI system that portends to explain how it works, how do we know whether the explanation works and the user has achieved a pragmatic understanding of the AI? This question entails some key concepts of measurement such as explanation goodness and trust. We present methods for enabling developers and researchers to: (1) Assess the a priori goodness of explanations, (2) Assess users' satisfaction with explanations, (3) Reveal user's mental model of an AI system, (4) Assess user's curiosity or need for explanations, (5) Assess whether the user's trust and reliance on the AI are appropriate, and finally, (6) Assess how the human-XAI work system performs. The methods we present derive from our integration of extensive research literatures and our own psychometric evaluations. We point to the previous research that led to the measurement scales which we aggregated and tailored specifically for the XAI context. Scales are presented in sufficient detail to enable their use by XAI researchers. For Mental Model assessment and Work System Performance, XAI researchers have choices. We point to a number of methods, expressed in terms of methods' strengths and weaknesses, and pertinent measurement issues.
Author Klein, Gary
Litman, Jordan
Hoffman, Robert R.
Mueller, Shane T.
Author_xml – sequence: 1
  givenname: Robert R.
  surname: Hoffman
  fullname: Hoffman, Robert R.
– sequence: 2
  givenname: Shane T.
  surname: Mueller
  fullname: Mueller, Shane T.
– sequence: 3
  givenname: Gary
  surname: Klein
  fullname: Klein, Gary
– sequence: 4
  givenname: Jordan
  surname: Litman
  fullname: Litman, Jordan
BookMark eNp9kc9u3CAQxlGUSkmTvEBPPMB6yx8b495WUZqulKqX5owGPKRENqwAS82pr17vJpWqHnoa5mO-3yC-9-Q8poiEfOBsK6UePnqX5sNWMCG3nA1KdP0ZuRRKtM2gB33-1_mC3JTyzBgTHeed7i_Jr68IZclYqE-Z4s_DBCGCnZDu9p_o3bGPUEOK9CmlMWIpG7oUzLSsavHgjncbOmOsMNE5jTitE27JIZVQXza05qXUDYU40h_LDLHZ7ekB87ptbRxek3cepoI3b_WKPH6--377pXn4dr-_3T00TnZ9bTzzHlTf8dELUAMOioNre6fVOAo1qtZa4RRyIRwg99baTrJWaildqxmz8orsX7ljgmdzyGGG_GISBHMSUn4ykGtwExrNkTtoO7miW2YtSLnCBmW5VhoQV5Z-ZbmcSsnojQv19Ek1Q5gMZ-aYiznlYo65mLdcVqv4x_rnKf8x_Qai05Zp
CitedBy_id crossref_primary_10_1002_sdr_70011
crossref_primary_10_1016_j_compind_2024_104233
crossref_primary_10_1002_jocb_70011
crossref_primary_10_3389_fcomp_2023_1117848
crossref_primary_10_1109_THMS_2025_3582285
crossref_primary_10_1080_10447318_2025_2468783
crossref_primary_10_3390_app142311288
crossref_primary_10_1080_0144929X_2025_2535732
crossref_primary_10_1007_s10639_025_13741_z
crossref_primary_10_4236_jfrm_2025_143011
crossref_primary_10_1080_10447318_2025_2542881
crossref_primary_10_1016_j_ijhcs_2025_103455
crossref_primary_10_3390_math12071024
crossref_primary_10_4018_JGIM_354062
crossref_primary_10_3389_frai_2024_1456486
crossref_primary_10_1016_j_ijmedinf_2025_105943
crossref_primary_10_1080_10447318_2025_2536617
crossref_primary_10_1080_09540091_2025_2507180
crossref_primary_10_1108_JSIT_08_2024_0297
crossref_primary_10_1007_s43681_024_00450_5
crossref_primary_10_17749_2070_4909_farmakoekonomika_2025_328
crossref_primary_10_1111_nin_70025
crossref_primary_10_1016_j_sftr_2025_101152
crossref_primary_10_1080_10447318_2025_2482742
crossref_primary_10_1016_j_chb_2025_108793
crossref_primary_10_1145_3709152
crossref_primary_10_1002_mar_22186
crossref_primary_10_1007_s13218_023_00806_9
crossref_primary_10_1080_1553118X_2025_2515277
crossref_primary_10_1108_JSIT_06_2024_0217
crossref_primary_10_1080_10447318_2025_2470278
crossref_primary_10_1002_aaai_12184
crossref_primary_10_1016_j_enbuild_2025_116246
crossref_primary_10_1186_s12911_025_03045_0
crossref_primary_10_3389_frobt_2024_1375490
crossref_primary_10_1016_j_techsoc_2024_102685
crossref_primary_10_1016_j_infsof_2024_107456
crossref_primary_10_1007_s10796_025_10609_y
crossref_primary_10_1007_s10660_025_09961_7
crossref_primary_10_1177_02666669241269666
crossref_primary_10_1109_ACCESS_2023_3329257
crossref_primary_10_3389_frai_2025_1582880
crossref_primary_10_1515_icom_2024_0014
crossref_primary_10_3389_fcomp_2023_1114806
crossref_primary_10_1016_j_knosys_2024_112305
crossref_primary_10_1177_10711813251368829
crossref_primary_10_1186_s42400_024_00241_9
crossref_primary_10_1016_j_cogsys_2024_101297
crossref_primary_10_1007_s00521_024_10951_3
crossref_primary_10_1016_j_procir_2024_10_134
crossref_primary_10_1007_s00146_025_02185_1
crossref_primary_10_1016_j_csbj_2025_04_021
crossref_primary_10_1109_LRA_2025_3579217
crossref_primary_10_4018_JGIM_372177
crossref_primary_10_1007_s10489_024_05509_8
crossref_primary_10_1089_cyber_2024_87594_ceu
crossref_primary_10_1016_j_ergon_2025_103745
crossref_primary_10_1080_00295450_2024_2411153
Cites_doi 10.1002/bdm.3960020103
10.1016/0749-596X(92)90008-L
10.1177/0018720814547570
10.1177/0018720814561675
10.1207/s15516709cog2605_1
10.1006/ceps.1997.0977
10.1126/science.357.6346.22
10.1016/j.cognition.2004.12.009
10.1207/s15327752jpa8203_05
10.1017/CBO9781139173469
10.1109/MIS.2013.24
10.1037/0033-2909.110.3.499
10.1016/0004-3702(90)90093-F
10.1007/s10458-005-6825-4
10.1207/S15327566IJCE0401_04
10.1002/per.766
10.1146/annurev.cs.02.060187.002153
10.1111/cogs.12574
10.1145/3487065
10.7551/mitpress/7304.001.0001
10.1145/3453173
10.1109/MIS.2003.1249172
10.1145/3301275.3302316
10.1109/MIS.2011.32
10.1177/1071181320641077
10.1080/135467896394447
10.1109/MIS.2009.124
10.1109/MSPEC.2017.7906899
10.1177/0018720811411912
10.3758/BF03197085
10.1177/0018720814564422
10.1037/11164-000
10.1207/s15327752jpa4803_13
10.1016/S0020-7373(87)80013-5
10.1080/00140139608964474
10.7551/mitpress/3072.003.0014
10.1207/s15327752jpa8202_3
10.1016/S0020-7373(87)80020-2
10.1111/j.1467-8624.2006.00852.x
10.1007/BF00993037
10.1109/MSPEC.2017.7934229
10.1111/j.2044-8295.1988.tb02286.x
10.1002/dir.20091
10.2307/1416744
10.1145/383952.383991
10.1177/154193120104500406
10.4324/9781315044361-8
10.1016/j.jecp.2003.09.003
10.1016/S0020-7373(79)80035-8
10.1016/j.cogsys.2004.11.007
10.1177/0963721417695617
10.1518/001872000779656589
10.1207/s15516709cog1803_3
10.1145/1240624.1240630
10.1177/0018720816686248
10.1016/j.inffus.2019.12.012
10.1016/j.ejor.2010.09.003
10.1037/0033-2909.116.1.75
10.1086/667782
10.1080/00140139408964957
10.1145/3366485
10.1177/0018720812465081
10.1518/001872008X288574
10.4324/9781315789354-35
10.1207/s15327809jls0101_4
10.1006/imms.1993.1028
10.1207/s15516709cog0502_2
10.1016/S1071-5819(03)00038-7
10.1201/9781315593173-2
10.1518/hfes.46.1.50.30392
10.1016/j.apergo.2010.01.009
10.1201/b10716
10.1177/0018720815582261
10.1207/s1532690xci2304_4
10.1177/0018720815581940
10.1080/07370008.1985.9649008
10.2814/062663
10.1177/1555343416636515
10.1016/j.ssci.2009.03.015
10.1037/0022-3514.61.1.13
10.1016/j.tics.2016.08.001
10.1177/154193120204600311
10.1207/s15516709cog0401_4
10.1201/9781315572529-8
10.31234/osf.io/9pqez
10.1109/VIS49827.2021.9623268
10.1177/154193120104500807
10.2307/2579746
10.1207/s15516709cog1302_1
10.1007/978-0-585-34290-0_6
10.1007/BF01099424
10.21236/ADA225644
10.21236/ADA123387
10.1093/oxfordhb/9780198795872.013.17
10.1007/s13218-020-00636-z
10.1111/j.1740-9713.2014.00778.x
10.1146/annurev-psych-113011-143823
10.1257/089533005775196732
10.1201/9781420005684
10.1109/MIS.2002.988440
10.1518/001872007X230154
10.1177/154193128703100123
10.1518/001872008X250601
10.1207/s15516709cog0000_70
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.3389/fcomp.2023.1096257
DatabaseName CrossRef
DOAJ Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2624-9898
ExternalDocumentID oai_doaj_org_article_81e1ca453dd240bba3353096b1868aee
10_3389_fcomp_2023_1096257
GroupedDBID 9T4
AAFWJ
AAYXX
ADMLS
AFPKN
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
M~E
OK1
ID FETCH-LOGICAL-c357t-f0ffa6751df2a69e961ac47c86dd26d64bb2c6e122cae1fbbb53043833c4800b3
IEDL.DBID DOA
ISICitedReferencesCount 95
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000935120200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2624-9898
IngestDate Fri Oct 03 12:50:24 EDT 2025
Sat Nov 29 02:11:56 EST 2025
Tue Nov 18 21:40:49 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c357t-f0ffa6751df2a69e961ac47c86dd26d64bb2c6e122cae1fbbb53043833c4800b3
OpenAccessLink https://doaj.org/article/81e1ca453dd240bba3353096b1868aee
ParticipantIDs doaj_primary_oai_doaj_org_article_81e1ca453dd240bba3353096b1868aee
crossref_citationtrail_10_3389_fcomp_2023_1096257
crossref_primary_10_3389_fcomp_2023_1096257
PublicationCentury 2000
PublicationDate 2023-02-06
PublicationDateYYYYMMDD 2023-02-06
PublicationDate_xml – month: 02
  year: 2023
  text: 2023-02-06
  day: 06
PublicationDecade 2020
PublicationTitle Frontiers in computer science (Lausanne)
PublicationYear 2023
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References Bainbridge (B6) 1979; 11
Carley (B22) 1992; 70
McKeown (B105) 1987; 2
Cahour (B18) 2009; 47
Fryer (B51) 1939; 52
Holzinger (B76) 2020; 34
Sarter (B142) 1997
B159
Montague (B114) 2010; 41
Fernbach (B45) 2012; 39
Mueller (B119) 2011
Polson (B129) 1988
Carberry (B21) 1990; 11
Chancey (B25) 2015; 57
Johnson-Laird (B80) 1980; 4
Litman (B98) 2010; 24
Carroll (B23) 1984; 1
de Kleer (B34) 1983
Heiser (B63) 2006; 30
Greeno (B58) 1983
Anderson (B3) 2020; 10
Muir (B122) 1996; 39
Kucala (B93) 2013
Rosenblit (B140) 2002; 26
Feltovich (B44) 2001
Shadbolt (B147) 2002; 20
Van Lehn (B155) 1990
Young (B163) 1983
Evans (B42) 2001
Chi (B29) 1981; 5
Chi (B26) 1989; 13
St-Cyr (B150) 2002
B2
Moray (B117) 1987; 7
Hoff (B66) 2015; 57
Praetorious (B131) 1988
Staggers (B149) 1993; 38
Taylor (B152) 1988
Hoffman (B68) 2010
Riley (B137) 1996
Rittle-Johnson (B139) 2006; 77
Merritt (B109) 2015; 57
B43
Hoffman (B72) 2013; 28
Byrne (B16) 2017; 26
Clancey (B31) 1986; 7
Hoffman (B70) 2001
Muir (B121) 1994; 37
Woods (B162) 2006
Schaffernicht (B144) 2011; 210
Novak (B125) 1984
Merritt (B107) 2013; 55
Frederick (B49) 2005; 19
Koehler (B90) 1991; 110
Biran (B12) 2017
Schaefer (B143) 2013
Tullio (B153) 2007
Gentner (B52) 1983
Johnson-Laird (B81) 1983
Pop (B130) 2015; 57
Crandall (B33) 2006
diSessa (B35) 1993; 10
Goodstein (B56) 1988
Hoffman (B67) 1989
Ritter (B138) 1988
Berry (B11) 1988; 79
Ford (B48) 1993
Klein (B86) 2016; 10
Goyal (B57) 2019
Khanna (B84) 2021; 12
Maheswaran (B103) 1991; 61
Fitzhugh (B46) 2011
Hardiman (B59) 1989; 17
Mills (B111) 2004; 87
Samurcay (B141) 1996; 59
Hoffman (B74) 2018
Clement (B32) 2004
Hoffman (B69) 2017
Hilton (B65) 1996; 2
Friedman (B50) 2017; 42
Mitchell (B112) 1989; 2
Beach (B8) 1992
Gentner (B53) 1983
Harford (B60) 2014; 11
Moon (B115) 2011
Hoffman (B75) 2009; 24
Dzindolet (B38) 2003; 58
Madhavan (B102) 2007; 49
Hoffman (B71) 2017; 59
Anderson (B4) 1990
Glenberg (B54) 1992; 31
Merritt (B106) 2011; 53
Doyle (B37) 2002
Huynh (B77) 2006; 13
Cacioppo (B17) 1984; 48
Hilton (B64) 1996; 2
Forbus (B47) 2001
Clancey (B30) 1984
B113
May (B104) 1993; 3
B110
Johnson-Laird (B82) 1989
Bogacz (B14) 2004; 6
Kashdan (B83) 2004; 82
Klein (B87) 2008
Merritt (B108) 2008; 50
Wickens (B160) 2015; 57
Johnson (B79) 2007; 21
Bjork (B13) 2013; 64
Psotka (B133) 1988
Champlin (B24) 2017; 54
Dodge (B36) 2021
Goodman (B55) 2016
B73
Lee (B94) 2004; 46
Harris (B61) 1984
Lombrozo (B100) 2016; 20
B127
B128
Moore (B116) 1990; 90
Muir (B120) 1987; 27
B124
Williams (B161) 1983
Cañas (B20) 2003
Kintsch (B85) 1984
O'Reilly (B126) 1998; 23
Berlyne (B9) 1960
Koopman (B91) 2003; 18
Arrieta (B5) 2020; 58
Voosen (B157) 2017; 357
Berlyne (B10) 1978; 2
Calin-Jageman (B19) 2005; 23
Mueller (B118) 2019
Chi (B28) 1991; 1
B88
Rasmussen (B135) 1986
Schraagen (B145) 2020
Lombrozo (B101) 2006; 99
Hawkins (B62) 2017; 54
Litman (B97) 2004; 82
(B41) 2022
Zhang (B164) 1987
Sleeman (B148) 1982
Tabatabai (B151) 2021
B92
Rasmussen (B136) 1994
Adams (B1) 2003
Chi (B27) 1994; 18
Lesgold (B95) 1992
Ward (B158) 2019
Klein (B89) 2001
B15
Jian (B78) 2000; 4
van der Veer (B154) 2003
B146
Loewenstein (B99) 1994; 116
Muramatsu (B123) 2001
Ehsan (B39) 2019
Prietula (B132) 2000; 42
Ericsson (B40) 1984
van Lent (B156) 2004
Qin (B134) 1992
Lippa (B96) 2008; 50
Bainbridge (B7) 1988
References_xml – year: 1988
  ident: B133
  publication-title: Intelligent Tutoring Systems: Lessons Learned
– year: 2013
  ident: B143
  publication-title: The perception and measurement of human-robot trust
– start-page: 197
  year: 2011
  ident: B46
  article-title: “Active trust management,”
  publication-title: Trust in Military Teams
– volume: 2
  start-page: 25
  year: 1989
  ident: B112
  article-title: Back to the future: Temporal perspective in the explanation of events
  publication-title: J. Behav. Decis. Making
  doi: 10.1002/bdm.3960020103
– volume: 31
  start-page: 129
  year: 1992
  ident: B54
  article-title: Comprehension of illustrated text: Pictures help to build mental models
  publication-title: J. Memory Lang.
  doi: 10.1016/0749-596X(92)90008-L
– volume: 57
  start-page: 407
  year: 2015
  ident: B66
  article-title: Trust in automation: Integrating empirical evidence on factors that influence trust
  publication-title: Human Factors
  doi: 10.1177/0018720814547570
– year: 1984
  ident: B85
  publication-title: Methods and Tactics in Cognitive Science.
– volume: 57
  start-page: 34
  year: 2015
  ident: B109
  article-title: Are well-calibrated users effective users? Associations between calibration of trust and performance on an automation- aided task
  publication-title: Human Factors
  doi: 10.1177/0018720814561675
– volume: 26
  start-page: 521
  year: 2002
  ident: B140
  article-title: The misunderstood limits of folk science: An illusion of explanatory depth
  publication-title: Cogn. Sci.
  doi: 10.1207/s15516709cog2605_1
– year: 1994
  ident: B136
  publication-title: Cognitive Systems Engineering.
– year: 2017
  ident: B12
  article-title: “Explanation and Justification in Machine Learning: A Survey,”
  publication-title: IJCAI-17 Workshop on Explainable Artificial Intelligence (XAI)
– year: 1983
  ident: B81
  publication-title: Mental Models: Towards a Cognitive Science of Language, Inference, and Consciousness
– volume: 23
  start-page: 434
  year: 1998
  ident: B126
  article-title: A comparison of self-explanation and elaborative interrogation
  publication-title: Contemp. Educ. Psychol.
  doi: 10.1006/ceps.1997.0977
– volume: 357
  start-page: 22
  year: 2017
  ident: B157
  article-title: How AI detectives are cracking open the black box of deep learning
  publication-title: Science
  doi: 10.1126/science.357.6346.22
– year: 2001
  ident: B47
  publication-title: Smart Machines in Education
– volume: 99
  start-page: 167
  year: 2006
  ident: B101
  article-title: Functional explanation and the function of explanation
  publication-title: Cognition
  doi: 10.1016/j.cognition.2004.12.009
– volume: 82
  start-page: 291
  year: 2004
  ident: B83
  article-title: Curiosity and exploration: Facilitating positive subjective experiences and personal growth opportunities
  publication-title: J. Person. Assess.
  doi: 10.1207/s15327752jpa8203_05
– year: 1984
  ident: B125
  publication-title: Learning How to Learn.
  doi: 10.1017/CBO9781139173469
– start-page: 1050
  year: 1992
  ident: B134
  article-title: “Imagery as a process representation in problem solving,”
  publication-title: Proceedings of the Fourteenth Annual Conference of the Cognitive Science Society
– year: 2018
  ident: B74
  publication-title: Literature Review and Integration of Key Ideas for Explainable AI
– start-page: 349
  year: 2001
  ident: B44
  article-title: “Learners'(mis) understanding of important and difficult concepts: A challenge to smart machines in education,”
  publication-title: Smart Machines in Education
– volume: 28
  start-page: 84
  year: 2013
  ident: B72
  article-title: Trust in automation
  publication-title: IEEE: Intell. Syst.
  doi: 10.1109/MIS.2013.24
– year: 2019
  ident: B57
  article-title: Counterfactual visual explanations
  publication-title: arXiv:1904.07451
– volume: 110
  start-page: 499
  year: 1991
  ident: B90
  article-title: Explanation, imagination, and confidence in judgement
  publication-title: Psychol. Bull
  doi: 10.1037/0033-2909.110.3.499
– year: 1982
  ident: B148
  publication-title: Intelligent Tutoring Systems
– year: 1990
  ident: B4
  article-title: “Cognitive modeling and intelligent tutoring,”
  publication-title: Artificial intelligence and learning environments
  doi: 10.1016/0004-3702(90)90093-F
– year: 2003
  ident: B20
  publication-title: A summary of literature pertaining to the use of concept mapping techniques and technologies for education and performance support
– start-page: 19
  year: 1996
  ident: B137
  article-title: “Operator reliance on automation: Theory and data,”
  publication-title: Automation Theory and Applications
– volume: 13
  start-page: 119
  year: 2006
  ident: B77
  article-title: An integrated trust and reputation model for open multi-agent systems
  publication-title: Autonomous Agents Multi-Agent Syst.
  doi: 10.1007/s10458-005-6825-4
– ident: B2
– volume: 4
  start-page: 53
  year: 2000
  ident: B78
  article-title: Foundations for an empirically determined scale of trust in automated systems
  publication-title: Int. J. Cogn. Ergon.
  doi: 10.1207/S15327566IJCE0401_04
– volume: 11
  start-page: 57
  year: 1990
  ident: B21
  article-title: Second international workshop on user modeling
  publication-title: AI Magaz.
– volume: 24
  start-page: 1
  year: 2010
  ident: B98
  article-title: Incurious motives to seek information about potential threats
  publication-title: Eur. J. Person.
  doi: 10.1002/per.766
– start-page: 233
  year: 1988
  ident: B152
  article-title: “Using cognitive models to make plants safer: Experimental and practical approaches,”
  publication-title: Tasks, errors and mental models
– volume: 2
  start-page: 401
  year: 1987
  ident: B105
  article-title: Language generation and explanation
  publication-title: Ann. Rev. Comput. Sci.
  doi: 10.1146/annurev.cs.02.060187.002153
– start-page: 52
  year: 2003
  ident: B154
  article-title: “Mental models,”
  publication-title: The human-computer interaction handbook
– volume: 42
  start-page: 1110
  year: 2017
  ident: B50
  article-title: Representing, running and revising mental models: A computational theory
  publication-title: Cogn. Sci.
  doi: 10.1111/cogs.12574
– volume: 12
  start-page: 1
  year: 2021
  ident: B84
  article-title: Finding AI's faults with AAR/AI: an empirical study
  publication-title: IEEE Trans. Inter. Intell. Syst.
  doi: 10.1145/3487065
– year: 2006
  ident: B33
  publication-title: Working Minds: A Practitioner's Guide to Cognitive Task Analysis.
  doi: 10.7551/mitpress/7304.001.0001
– start-page: 51
  year: 1984
  ident: B30
  article-title: “Methodology for building an intelligent tutoring system,”
  publication-title: Method and tactics in Cognitive Science
– year: 2021
  ident: B36
  article-title: After-action review for AI (AAR/AI)
  publication-title: ACM Trans. Intell. Syst.
  doi: 10.1145/3453173
– volume: 18
  start-page: 70
  year: 2003
  ident: B91
  article-title: Work-arounds, make-work, and kludges
  publication-title: IEEE: Intell. Syst.
  doi: 10.1109/MIS.2003.1249172
– volume: 1
  start-page: 125
  year: 1984
  ident: B23
  article-title: Minimalist training
  publication-title: Datamation
– year: 2019
  ident: B39
  doi: 10.1145/3301275.3302316
– year: 2011
  ident: B119
  article-title: Improving users' mental models of intelligent software tools
  publication-title: IEEE Intell. Syst.
  doi: 10.1109/MIS.2011.32
– year: 2020
  ident: B145
  article-title: “Trusting the X in XAI: Effects of different types of explanations by a self-driving car on trust, explanation satisfaction and mental models,”
  publication-title: Proceedings of the 2020 Human Factors and Ergonomics Society 64th International Annual Meeting.
  doi: 10.1177/1071181320641077
– volume: 2
  start-page: 273
  year: 1996
  ident: B64
  article-title: Mental models and causal explanation: Judgements of probable cause and explanatory relevance
  publication-title: Think. Reason.
  doi: 10.1080/135467896394447
– start-page: 57
  year: 2008
  ident: B87
  article-title: “Macrocognition, mental models, and cognitive task analysis methodology,”
  publication-title: Naturalistic decision making and macrocognition
– volume: 24
  start-page: 5
  year: 2009
  ident: B75
  article-title: The dynamics of trust in cyberdomains
  publication-title: IEEE Intell. Syst.
  doi: 10.1109/MIS.2009.124
– volume: 54
  start-page: 42
  year: 2017
  ident: B24
  article-title: AI medicine comes to Africa's rural clinics
  publication-title: IEEE Spectrum
  doi: 10.1109/MSPEC.2017.7906899
– volume: 53
  start-page: 356
  year: 2011
  ident: B106
  article-title: Affective processes in human–automation interactions
  publication-title: Human Factors.
  doi: 10.1177/0018720811411912
– ident: B110
– year: 2019
  ident: B118
  publication-title: Explanation in human-AI Systems: A Literature Meta-Review, synopsis of Key Ideas, and Publications, and Bibliography for Explainable AI.
– ident: B43
– start-page: 161
  year: 2001
  ident: B89
  article-title: “Some guidelines for conducting a cognitive task analysis,”
  publication-title: Human/technology interaction in complex systems
– volume: 17
  start-page: 627
  year: 1989
  ident: B59
  article-title: The relation between problem categorization and problem solving among experts and novices
  publication-title: Memory Cogn.
  doi: 10.3758/BF03197085
– volume: 57
  start-page: 545
  year: 2015
  ident: B130
  article-title: Individual differences in the calibration of trust in automation
  publication-title: Human Factors
  doi: 10.1177/0018720814564422
– year: 1960
  ident: B9
  publication-title: Conflict, Arousal, and Curiosity
  doi: 10.1037/11164-000
– year: 1986
  ident: B135
  publication-title: Information Processing and Human-Machine Interaction.
– start-page: 57
  year: 2013
  ident: B93
  publication-title: The truthiness of trustworthiness.
– volume: 48
  start-page: 306
  year: 1984
  ident: B17
  article-title: The efficient assessment of need for cognition
  publication-title: J. Person. Assess.
  doi: 10.1207/s15327752jpa4803_13
– start-page: 28
  year: 1989
  ident: B67
  article-title: “Whom (or what) do you trust: Historical reflections on the psychology and sociology of information technology,”
  publication-title: Proceedings of the Fourth Annual Symposium on Human Interaction with Complex Systems
– volume: 27
  start-page: 527
  year: 1987
  ident: B120
  article-title: Trust between humans and machines, and the design of decision aids
  publication-title: Int. J. Man–Mach. Stud.
  doi: 10.1016/S0020-7373(87)80013-5
– ident: B127
– volume: 39
  start-page: 429
  year: 1996
  ident: B122
  article-title: Trust in automation. Part II Experimental studies of trust and human intervention in a process control simulation
  publication-title: Ergonomics
  doi: 10.1080/00140139608964474
– start-page: 469
  year: 1989
  ident: B82
  article-title: “Mental models,”
  publication-title: Foundations of Cognitive Science
  doi: 10.7551/mitpress/3072.003.0014
– ident: B146
– volume: 82
  start-page: 147
  year: 2004
  ident: B97
  article-title: The measurement of curiosity as a feeling-of-deprivation
  publication-title: J. Person. Assess.
  doi: 10.1207/s15327752jpa8202_3
– year: 1988
  ident: B56
  publication-title: Tasks, errors and mental models.
– volume: 7
  start-page: 619
  year: 1987
  ident: B117
  article-title: Intelligent aids, mental models, and the theory of machines
  publication-title: Int. J. Man-Mach. Stud.
  doi: 10.1016/S0020-7373(87)80020-2
– volume: 77
  start-page: 1
  year: 2006
  ident: B139
  article-title: Promoting transfer: Effects of self-explanation and direct instruction
  publication-title: Child Development
  doi: 10.1111/j.1467-8624.2006.00852.x
– ident: B113
– volume: 2
  start-page: 97
  year: 1978
  ident: B10
  article-title: Curiosity and learning
  publication-title: Motiv. Emot.
  doi: 10.1007/BF00993037
– year: 2016
  ident: B55
  article-title: “European Union regulations on algorithmic decision-making and a ‘right to explanation.',”
  publication-title: Presented at the ICML Workshop on Human Interpretability in Machine Learning
– volume: 54
  start-page: 34
  year: 2017
  ident: B62
  article-title: Can we copy the brain? What intelligent machines need to learn from the Neocortex
  publication-title: IEEE Spectrum
  doi: 10.1109/MSPEC.2017.7934229
– volume: 79
  start-page: 251
  year: 1988
  ident: B11
  article-title: Interactive tasks and the implicit-explicit distinction
  publication-title: Br. J. Psychol.
  doi: 10.1111/j.2044-8295.1988.tb02286.x
– volume: 21
  start-page: 2
  year: 2007
  ident: B79
  article-title: Achieving customer value from electronic channels through identity commitment, calculative commitment, and trust in technology
  publication-title: J. Inter. Market.
  doi: 10.1002/dir.20091
– volume: 52
  start-page: 367
  year: 1939
  ident: B51
  article-title: Post quantification of introspective data
  publication-title: Am. J. Psychol.
  doi: 10.2307/1416744
– ident: B88
– year: 2001
  ident: B123
  article-title: “Transparent queries: Investigation users' mental models of search engines,”
  publication-title: Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
  doi: 10.1145/383952.383991
– year: 2001
  ident: B42
  article-title: “Mental model assessments: Is there convergence among different methods?,”
  publication-title: Proceedings of the Human Factors and Ergonomics Society 45th Annual Meeting
  doi: 10.1177/154193120104500406
– year: 1992
  ident: B95
  article-title: “SHERLOCK: A coached practice environment for an electronics troubleshooting job,”
  publication-title: Computer Assisted Instruction and Intelligent Tutoring Systems: Shared Issues and Complementary Approaches
  doi: 10.4324/9781315044361-8
– volume: 87
  start-page: 1
  year: 2004
  ident: B111
  article-title: Knowing the limits of one's understanding: The development of an awareness of an illusion of explanatory depth
  publication-title: J. Exper. Child Psychol.
  doi: 10.1016/j.jecp.2003.09.003
– year: 2003
  ident: B1
  publication-title: Trust in automated systems
– volume: 11
  start-page: 411
  year: 1979
  ident: B6
  article-title: Verbal reports as evidence of process operator's knowledge
  publication-title: Int. J. Man-Mach. Stud.
  doi: 10.1016/S0020-7373(79)80035-8
– volume: 6
  start-page: 312
  year: 2004
  ident: B14
  article-title: Understanding dynamic and static displays: Using images to reason dynamically
  publication-title: Cogn. Syst. Res.
  doi: 10.1016/j.cogsys.2004.11.007
– ident: B124
– volume: 26
  start-page: 314
  year: 2017
  ident: B16
  article-title: Counterfactual thinking: from logic to morality
  publication-title: Curr. Direct. Psychol. Sci.
  doi: 10.1177/0963721417695617
– ident: B15
– volume: 42
  start-page: 54
  year: 2000
  ident: B132
  article-title: Factors influencing analysis of complex cognitive tasks: A framework and example from industrial process control
  publication-title: Human Factors
  doi: 10.1518/001872000779656589
– volume: 18
  start-page: 439
  year: 1994
  ident: B27
  article-title: Eliciting self-explanations improves understanding
  publication-title: Cogn. Sci.
  doi: 10.1207/s15516709cog1803_3
– start-page: 155
  year: 1983
  ident: B34
– year: 2007
  ident: B153
  article-title: “How it works: a field study of non-technical users interacting with an intelligent system,”
  publication-title: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
  doi: 10.1145/1240624.1240630
– volume: 59
  start-page: 564
  year: 2017
  ident: B71
  article-title: Measuring resilience
  publication-title: Human Factors
  doi: 10.1177/0018720816686248
– start-page: 99
  year: 1983
  ident: B52
  article-title: “Flowing waters or teem crowds: Mental models of electricity,”
  publication-title: Mental models
– volume: 58
  start-page: 82
  year: 2020
  ident: B5
  article-title: Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI
  publication-title: Inform. Fusion
  doi: 10.1016/j.inffus.2019.12.012
– volume: 210
  start-page: 57
  year: 2011
  ident: B144
  article-title: A comprehensive method for comparing mental models of dynamical systems
  publication-title: Eur. J. Oper. Res.
  doi: 10.1016/j.ejor.2010.09.003
– volume: 116
  start-page: 75
  year: 1994
  ident: B99
  article-title: The psychology of curiosity: A review and reinterpretation
  publication-title: Psychol. Bull.
  doi: 10.1037/0033-2909.116.1.75
– volume: 39
  start-page: 1115
  year: 2012
  ident: B45
  article-title: Explanation friends and foes: How mechanistic detail determines understanding and preference
  publication-title: J. Cons. Res
  doi: 10.1086/667782
– volume: 37
  start-page: 1905
  year: 1994
  ident: B121
  article-title: Trust in automation Part 1: Theoretical issues in the study of trust and human intervention in automated systems
  publication-title: Ergonomics
  doi: 10.1080/00140139408964957
– volume: 10
  start-page: 1
  year: 2020
  ident: B3
  article-title: Mental models of mere mortals with explanations of reinforcement learning
  publication-title: ACM Trans. Inter. Intell. Syst.
  doi: 10.1145/3366485
– volume: 55
  start-page: 520
  year: 2013
  ident: B107
  article-title: I trust it, but don't know why: Effects of implicit attitudes toward automation in trust in an automated system
  publication-title: Human Factors
  doi: 10.1177/0018720812465081
– volume: 50
  start-page: 194
  year: 2008
  ident: B108
  article-title: Not all trust is created equal: Dispositional and history-based trust in human–automation interactions
  publication-title: Human Factors
  doi: 10.1518/001872008X288574
– year: 2004
  ident: B32
  article-title: “Imagistic simulation and physical intuition in expert problem solving,”
  publication-title: Proceedings of the Sixteenth Annual Conference of the Cognitive Science Society
  doi: 10.4324/9781315789354-35
– ident: B92
– volume: 1
  start-page: 69
  year: 1991
  ident: B28
  article-title: The content of physics self-explanations
  publication-title: J. Learn. Sci
  doi: 10.1207/s15327809jls0101_4
– start-page: 267
  year: 1984
  ident: B61
  article-title: “Machine intelligence in real systems: Some ergonomic issues,”
  publication-title: Human-Computer Interaction
– volume: 38
  start-page: 587
  year: 1993
  ident: B149
  article-title: Mental models: concepts for human-computer interaction research
  publication-title: Int. J. Man-Mach. Stud.
  doi: 10.1006/imms.1993.1028
– volume: 5
  start-page: 121
  year: 1981
  ident: B29
  article-title: Categorization and representation of physics problems by experts and novices
  publication-title: Cogn. Sci.
  doi: 10.1207/s15516709cog0502_2
– volume: 58
  start-page: 697
  year: 2003
  ident: B38
  article-title: The role of trust in automation reliance
  publication-title: Int. J. Hum. Comput. Stud.
  doi: 10.1016/S1071-5819(03)00038-7
– year: 2010
  ident: B68
  article-title: “Theory → Concepts → Measures but Policies → Metrics,”
  publication-title: Macrocognition metrics and scenarios: Design and evaluation for real-world teams
  doi: 10.1201/9781315593173-2
– volume: 46
  start-page: 50
  year: 2004
  ident: B94
  article-title: Trust in automation: Designing for appropriate reliance
  publication-title: Human Factors
  doi: 10.1518/hfes.46.1.50.30392
– start-page: 35
  year: 1983
  ident: B163
  article-title: “Surrogates and mappings: Two kinds of conceptual models of interactive devices,”
  publication-title: Mental Models
– volume: 41
  start-page: 812
  year: 2010
  ident: B114
  article-title: Validation of a trust in medical technology instrument
  publication-title: Appl. Ergon.
  doi: 10.1016/j.apergo.2010.01.009
– year: 2011
  ident: B115
  publication-title: Applied Concept Mapping: Capturing, Analyzing and Organizing Knowledge
  doi: 10.1201/b10716
– volume: 57
  start-page: 947
  year: 2015
  ident: B25
  article-title: The role of trust as a mediator between system characteristics and response behaviors
  publication-title: Human Factors
  doi: 10.1177/0018720815582261
– start-page: 285
  year: 1988
  ident: B138
  article-title: “Teaching real-time tactical thinking,”
  publication-title: Intelligent Tutoring Systems: Lessons Learned
– volume: 59
  start-page: 45
  year: 1996
  ident: B141
  article-title: Causal versus topographical support for diagnosis in a dynamic situation
  publication-title: Le Travail Humain
– start-page: 293
  year: 1988
  ident: B131
  article-title: “Verbal reports: A problem in research design,”
  publication-title: Tasks, Errors and Mental Models
– start-page: 900
  year: 2004
  ident: B156
  article-title: “An explainable artificial intelligence system for small-unit tactical behavior,”
  publication-title: Proceedings of the 19th National Conference on Artificial Intelligence
– volume: 90
  start-page: 457
  year: 1990
  ident: B116
  article-title: “Pointing: A Way Toward Explanation Dialogue,”
  publication-title: Proceedings of AAAI
– volume: 23
  start-page: 523
  year: 2005
  ident: B19
  article-title: The role of encoding in the self-explanation effect
  publication-title: Cogn. Instr.
  doi: 10.1207/s1532690xci2304_4
– volume: 57
  start-page: 728
  year: 2015
  ident: B160
  article-title: Complacency and automation bias in the use of imperfect automation
  publication-title: Human Factors
  doi: 10.1177/0018720815581940
– volume: 10
  start-page: 105
  year: 1993
  ident: B35
  article-title: Toward an epistemology of physics
  publication-title: Cogn. Instr.
  doi: 10.1080/07370008.1985.9649008
– year: 2002
  ident: B37
  article-title: “Mental models of dynamic systems,”
  publication-title: System Dynamics and Integrated Modeling, Encyclopedia of Life Support Systems
– year: 2022
  ident: B41
  publication-title: AI-powered Trademark Dispute Resolution - Expert Opinion Commissioned by the European Union Intellectual Property Office (EUIPO).
  doi: 10.2814/062663
– volume: 10
  start-page: 268
  year: 2016
  ident: B86
  article-title: The ShadowBox approach to cognitive skills training: an empirical evaluation
  publication-title: J. Cogn. Eng. Decis. Mak.
  doi: 10.1177/1555343416636515
– volume: 47
  start-page: 1260
  year: 2009
  ident: B18
  article-title: Does projection into use improve trust and exploration? An example with a cruise control system
  publication-title: Safety Sci.
  doi: 10.1016/j.ssci.2009.03.015
– volume: 61
  start-page: 13
  year: 1991
  ident: B103
  article-title: Promoting systematic processing in low-motivation settings: Effect of incongruent information on processing and judgment
  publication-title: J. Person. Soc. Psychol.
  doi: 10.1037/0022-3514.61.1.13
– volume: 20
  start-page: 748
  year: 2016
  ident: B100
  article-title: Explanatory preferences shape learning and inference
  publication-title: Trends Cogn. Sci.
  doi: 10.1016/j.tics.2016.08.001
– start-page: 70
  year: 1988
  ident: B7
  article-title: “Types of representation,”
  publication-title: Tasks, errors and mental models
– year: 2002
  ident: B150
  article-title: “Mental models and ecological interface design: An experimental investigation,”
  publication-title: Proceedings of the Human Factors and Ergonomic Society Annual Meeting
  doi: 10.1177/154193120204600311
– volume: 4
  start-page: 71
  year: 1980
  ident: B80
  article-title: Mental models in cognitive science
  publication-title: Cogn. Sci.
  doi: 10.1207/s15516709cog0401_4
– year: 2017
  ident: B69
  article-title: “A Taxonomy of Emergent Trusting in the Human–Machine Relationship,”
  publication-title: Cognitive Systems Engineering: The Future for a Changing World
  doi: 10.1201/9781315572529-8
– year: 1984
  ident: B40
  publication-title: Protocol Analysis: Verbal Reports as Data.
– ident: B73
  doi: 10.31234/osf.io/9pqez
– start-page: 131
  year: 1983
  ident: B161
  article-title: “Human reasoning about a simple physical system,”
  publication-title: Mental Models
– year: 2021
  ident: B151
  publication-title: Proceedings of the 2021 IEEE Visualization Conference
  doi: 10.1109/VIS49827.2021.9623268
– year: 2001
  ident: B70
  article-title: “STORM-LK: A human-centered knowledge model for weather forecasting,”
  publication-title: Proceedings of the 45th Annual Meeting of the Human Factors and Ergonomics Society
  doi: 10.1177/154193120104500807
– start-page: 1926
  year: 1997
  ident: B142
  article-title: “Automation surprises,”
  publication-title: Handbook of Human Factors/Ergonomics
– volume: 70
  start-page: 601
  year: 1992
  ident: B22
  article-title: Extracting, representing and analyzing mental models
  publication-title: Soc. Forces
  doi: 10.2307/2579746
– volume: 13
  start-page: 145
  year: 1989
  ident: B26
  article-title: Self-explanations: How students study and use examples in learning to solve problems
  publication-title: Cogn. Sci.
  doi: 10.1207/s15516709cog1302_1
– year: 1992
  ident: B8
  article-title: “Epistemic strategies on causal thinking in expert and nonexpert judgment,”
  publication-title: Expertise and decision support
  doi: 10.1007/978-0-585-34290-0_6
– volume: 3
  start-page: 27
  year: 1993
  ident: B104
  article-title: Using structural descriptions of interfaces to automate the modeling of user cognition
  publication-title: User Model. User-Adapted Inter.
  doi: 10.1007/BF01099424
– year: 1990
  ident: B155
  publication-title: Explanation-based learning of correctness: Towards a model of the self-explanation effect
  doi: 10.21236/ADA225644
– year: 1983
  ident: B58
  article-title: “Conceptual entities,”
  publication-title: Mental Models
  doi: 10.21236/ADA123387
– year: 2019
  ident: B158
  article-title: “An historical perspective on introspection: Implications and guidelines for eliciting verbal and introspective-type reports,”
  publication-title: The Oxford Handbook of Expertise
  doi: 10.1093/oxfordhb/9780198795872.013.17
– year: 1983
  ident: B53
  publication-title: Mental Models
– volume: 34
  start-page: 193
  year: 2020
  ident: B76
  article-title: Measuring the quality of explanations: the System Causability Scale
  publication-title: Kunstliche Intell.
  doi: 10.1007/s13218-020-00636-z
– volume: 11
  start-page: 14
  year: 2014
  ident: B60
  article-title: Big data: Are we making a big mistake?
  publication-title: Significance
  doi: 10.1111/j.1740-9713.2014.00778.x
– volume: 64
  start-page: 417
  year: 2013
  ident: B13
  article-title: Self-regulated learning: Beliefs, techniques, and illusions
  publication-title: Ann. Rev. Psychol.
  doi: 10.1146/annurev-psych-113011-143823
– volume: 19
  start-page: 25
  year: 2005
  ident: B49
  article-title: Cognitive reflection and decision making
  publication-title: J. Econ. Perspect.
  doi: 10.1257/089533005775196732
– year: 2006
  ident: B162
  publication-title: Joint Cognitive Systems: Patterns in Cognitive Systems Engineering
  doi: 10.1201/9781420005684
– start-page: 111
  year: 1993
  ident: B48
  article-title: “Participatory explanation,”
  publication-title: Presented at the FLAIRS 93: Sixth Florida Artificial Intelligence Research Symposium (FLAIRS)
– ident: B159
– volume: 20
  start-page: 30
  year: 2002
  ident: B147
  article-title: A matter of trust
  publication-title: IEEE Intell. Syst.
  doi: 10.1109/MIS.2002.988440
– volume: 49
  start-page: 773
  year: 2007
  ident: B102
  article-title: Effects of information source, pedigree, and reliability on operator interaction with decision support systems
  publication-title: Human Factors
  doi: 10.1518/001872007X230154
– year: 1988
  ident: B129
  publication-title: Foundations of Intelligent Tutoring Systems.
– ident: B128
– year: 1987
  ident: B164
  article-title: “A study of the mental model of a complex dynamic system: The effect of display aiding and contextual system training,”
  publication-title: Proceedings of the Human Factors and Ergonomics Society 31st Annual Meeting
  doi: 10.1177/154193128703100123
– volume: 7
  start-page: 40
  year: 1986
  ident: B31
  article-title: From GUIDON to NEOMYCIN and HERACLES in twenty short lessons
  publication-title: AI Magazine
– volume: 2
  start-page: 273
  year: 1996
  ident: B65
  article-title: Mental models and causal explanation: Judgements of probable cause and explanatory relevance
  publication-title: Thinking Reason.
  doi: 10.1080/135467896394447
– volume: 50
  start-page: 112
  year: 2008
  ident: B96
  article-title: Everyday expertise: Cognitive demands in diabetes self-management
  publication-title: Human Factors
  doi: 10.1518/001872008X250601
– volume: 30
  start-page: 581
  year: 2006
  ident: B63
  publication-title: Cogn. Sci.
  doi: 10.1207/s15516709cog0000_70
SSID ssj0002511587
Score 2.5865052
SecondaryResourceType review_article
Snippet If a user is presented an AI system that portends to explain how it works, how do we know whether the explanation works and the user has achieved a pragmatic...
SourceID doaj
crossref
SourceType Open Website
Enrichment Source
Index Database
SubjectTerms explanation goodness
explanatory reasoning
machine-generated explanations
measurement
mental models
trust
Title Measures for explainable AI: Explanation goodness, user satisfaction, mental models, curiosity, trust, and human-AI performance
URI https://doaj.org/article/81e1ca453dd240bba3353096b1868aee
Volume 5
WOSCitedRecordID wos000935120200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2624-9898
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002511587
  issn: 2624-9898
  databaseCode: DOA
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2624-9898
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002511587
  issn: 2624-9898
  databaseCode: M~E
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQxcDCG1Fe8sBGQ-s6cWy2goqoRCsGQN0iP1mqtqIIwQJ_nTsnLWWBhSVD5ETW57Pvzrr7PkJOkQEdvLpMbAhZkuYuTbRXMjFIRmaYy2WUZHm8zQcDORyquyWpL6wJK-mBS-CaknlmdZpx58D5GKM5zzjE3QZ53rX3ePq2crWUTOEZjIFzJvOySwayMNUMWKJ9jmLhyKAEUX_-wxMtEfZHz3K9SdarkJB2yqlskRU_3iYbc7kFWu2-HfLZL-_zZhQCTerfpqOq84l2ehcUi-l0ebVHnyYTh0dYg-IdBJ0tdTA0aMnmT6MEDozA63Ys3Hpv0Nh_0aB67GiU7ks6PTr9bizYJQ_X3furm6TST0gsz_KXJLRC0JAQMBfaWiivBNM2za0UgKVwIjWmbYVn7bbVngVjDCCL1KXcphBHGr5HauPJ2O8TCrucB2Ut19akXCgpWlqGIJl10isj64TNsSxsRS6OGhejApIMxL-I-BeIf1HhXydni2-mJbXGr6MvcYkWI5EWO74AYykqYyn-MpaD__jJIVnDicXSbXFEarA4_pis2ldYy-eTaIfw7H90vwD3WOUY
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Measures+for+explainable+AI%3A+Explanation+goodness%2C+user+satisfaction%2C+mental+models%2C+curiosity%2C+trust%2C+and+human-AI+performance&rft.jtitle=Frontiers+in+computer+science+%28Lausanne%29&rft.au=Robert+R.+Hoffman&rft.au=Shane+T.+Mueller&rft.au=Gary+Klein&rft.au=Jordan+Litman&rft.date=2023-02-06&rft.pub=Frontiers+Media+S.A&rft.eissn=2624-9898&rft.volume=5&rft_id=info:doi/10.3389%2Ffcomp.2023.1096257&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_81e1ca453dd240bba3353096b1868aee
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2624-9898&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2624-9898&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2624-9898&client=summon