{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T21:16:09Z","timestamp":1780607769098,"version":"3.54.1"},"reference-count":85,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T00:00:00Z","timestamp":1722556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Interact. Intell. Syst."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>\n            Trust calibration is essential in AI-assisted decision-making. If human users understand the rationale on which an AI model has made a prediction, they can decide whether they consider this prediction reasonable. Especially in high-risk tasks such as mushroom hunting (where a wrong decision may be fatal), it is important that users make correct choices to trust or overrule the AI. Various explainable AI (XAI) methods are currently being discussed as potentially useful for facilitating understanding and subsequently calibrating user trust. So far, however, it remains unclear which approaches are most effective. In this article, the effects of XAI methods on human AI-assisted decision-making in the high-risk task of mushroom picking were tested. For that endeavor, the effects of (i) Grad-CAM attributions, (ii) nearest-neighbor examples, and (iii) network-dissection concepts were compared in a between-subjects experiment with\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(N=501\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            participants representing end-users of the system. In general, nearest-neighbor examples improved decision correctness the most. However, varying effects for different task items became apparent. All explanations seemed to be particularly effective when they revealed reasons to (i) doubt a specific AI classification when the AI was wrong and (ii) trust a specific AI classification when the AI was correct. Our results suggest that well-established methods, such as Grad-CAM attribution maps, might not be as beneficial to end users as expected and that XAI techniques for use in real-world scenarios must be chosen carefully.\n          <\/jats:p>","DOI":"10.1145\/3665647","type":"journal-article","created":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T16:41:10Z","timestamp":1716396070000},"page":"1-36","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Reassuring, Misleading, Debunking: Comparing Effects of XAI Methods on Human Decisions"],"prefix":"10.1145","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0249-4062","authenticated-orcid":false,"given":"Christina","family":"Humer","sequence":"first","affiliation":[{"name":"Johannes Kepler University Linz, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4101-5180","authenticated-orcid":false,"given":"Andreas","family":"Hinterreiter","sequence":"additional","affiliation":[{"name":"Johannes Kepler University Linz, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9062-0996","authenticated-orcid":false,"given":"Benedikt","family":"Leichtmann","sequence":"additional","affiliation":[{"name":"Johannes Kepler University Linz, Linz, Austria and Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3447-0556","authenticated-orcid":false,"given":"Martina","family":"Mara","sequence":"additional","affiliation":[{"name":"Johannes Kepler University Linz, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9186-2092","authenticated-orcid":false,"given":"Marc","family":"Streit","sequence":"additional","affiliation":[{"name":"Johannes Kepler University Linz, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,2]]},"reference":[{"key":"e_1_3_4_2_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"31","author":"Adebayo Julius","year":"2018","unstructured":"Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, and Been Kim. 2018. Sanity checks for saliency maps. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 31. Retrieved from https:\/\/papers.nips.cc\/paper\/2018\/hash\/294a8ed24b1ad22ec2e7efea049b8737-Abstract.html"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.09.002"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377325.3377519"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907375117"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1214\/11-AOAS495"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511139"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1080\/00275514.2018.1479561"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1521-4036(200001)42:1<17::AID-BIMJ17>3.0.CO;2-U"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377325.3377498"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3301275.3302289"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14034"},{"key":"e_1_3_4_16_2","unstructured":"Eric Chu Deb Roy and Jacob Andreas. 2020. Are visual explanations useful? A case study in model-in-the-loop prediction. arXiv:2007.12248. Retrieved from http:\/\/arxiv.org\/abs\/2007.12248"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771587"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1177\/0956797613504966"},{"key":"e_1_3_4_19_2","first-page":"6970","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"30","author":"Dabkowski Piotr","year":"2017","unstructured":"Piotr Dabkowski and Yarin Gal. 2017. Real time image saliency for black box classifiers. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 30, 6970\u20136979. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/0060ef47b12160b9198302ebdb144dcf-Abstract.html"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26633-6_13"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3359786"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1955.10501294"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3441342"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3503727"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517734"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v8i1.7462"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.3758\/BF03193146"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1177\/001316447303300309"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.07722arXiv"},{"key":"e_1_3_4_30_2","first-page":"1050","volume-title":"Proceedings of The 33rd International Conference on Machine Learning","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of The 33rd International Conference on Machine Learning. 1050\u20131059. Retrieved from https:\/\/proceedings.mlr.press\/v48\/gal16.html"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3236009"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511158"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsbl.2019.0174"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN50785.2021.9515513"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610067"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581025"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.1177\/0018720814547570"},{"key":"e_1_3_4_40_2","doi-asserted-by":"publisher","unstructured":"Robert R. Hoffman Shane T. Mueller Gary Klein and Jordan Litman. 2019. Metrics for explainable AI: challenges and prospects. arXiv:1812.04608. Retrieved from 10.48550\/arXiv.1812.04608 [cs] version: 2.","DOI":"10.48550\/arXiv.1812.04608"},{"key":"e_1_3_4_41_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"32","author":"Hooker Sara","year":"2019","unstructured":"Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, and Been Kim. 2019. A benchmark for interpretability methods in deep neural networks. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 32. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/fe4b8556000d0f0cae99daa5c5c5a410-Abstract.html"},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","unstructured":"Christina Humer Andreas Hinterreiter Benedikt Leichtmann Martina Mara and Marc Streit. 2022. Effects of Explainable Artificial Intelligence Methods on Human Trust and Behavior: A Comparison of Nearest Neighbor Grad-CAM and Network Dissection. DOI: 10.17605\/OSF.IO\/SD953","DOI":"10.17605\/OSF.IO\/SD953"},{"key":"e_1_3_4_43_2","first-page":"4211","article-title":"How can i explain this to you? An empirical study of deep neural network explanation methods","volume":"33","author":"Jeyakumar Jeya Vikranth","year":"2020","unstructured":"Jeya Vikranth Jeyakumar, Joseph Noor, Yu-Hsi Cheng, Luis Garcia, and Mani Srivastava. 2020. How can i explain this to you? An empirical study of deep neural network explanation methods. Advances in Neural Information Processing Systems 33 (2020), 4211\u20134222.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(21)00039-X"},{"key":"e_1_3_4_45_2","unstructured":"Weina Jin Xiaoxiao Li and Ghassan Hamarneh. 2023. The XAI alignment problem: Rethinking how should we evaluate human-centered AI explainability techniques. arXiv:2303.17707. Retrieved from http:\/\/arxiv.org\/abs\/2303.17707 [cs]."},{"key":"e_1_3_4_46_2","doi-asserted-by":"publisher","DOI":"10.1901\/jeab.2002.77-129"},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376219"},{"key":"e_1_3_4_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103459"},{"key":"e_1_3_4_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581001"},{"key":"e_1_3_4_50_2","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525433"},{"key":"e_1_3_4_51_2","doi-asserted-by":"publisher","DOI":"10.1177\/0018720819853686"},{"key":"e_1_3_4_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96074-6_2"},{"key":"e_1_3_4_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501999"},{"key":"e_1_3_4_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375833"},{"key":"e_1_3_4_55_2","doi-asserted-by":"publisher","DOI":"10.2307\/2529310"},{"key":"e_1_3_4_56_2","volume-title":"Proceedings of the 2020 Workshop on Explainable Smart Systems for Algorithmic Transparency in Emerging Technologies, 2582","author":"Larasati Retno","year":"2020","unstructured":"Retno Larasati, Anna De Liddo, and Enrico Motta. 2020. The effect of explanation styles on user\u2019s trust. In Proceedings of the 2020 Workshop on Explainable Smart Systems for Algorithmic Transparency in Emerging Technologies, 2582."},{"key":"e_1_3_4_57_2","doi-asserted-by":"publisher","DOI":"10.1518\/hfes.46.1.50_30392"},{"key":"e_1_3_4_58_2","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2023.2221605"},{"key":"e_1_3_4_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2022.107539"},{"key":"e_1_3_4_60_2","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2024.2331878"},{"key":"e_1_3_4_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_3_4_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376727"},{"key":"e_1_3_4_63_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295230"},{"key":"e_1_3_4_64_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrp.2013.09.008"},{"key":"e_1_3_4_65_2","doi-asserted-by":"publisher","DOI":"10.1518\/001872008X288574"},{"key":"e_1_3_4_66_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"e_1_3_4_67_2","volume-title":"Interpretable Machine Learning: A Guide for Making Black Box Models Explainable","author":"Molnar Christoph","year":"2022","unstructured":"Christoph Molnar. 2022. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable (2nd ed.). Retrieved from christophm.github.io\/interpretable-ml-book\/","edition":"2"},{"key":"e_1_3_4_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579481"},{"key":"e_1_3_4_69_2","doi-asserted-by":"publisher","DOI":"10.1002\/pra2.487"},{"key":"e_1_3_4_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3334480.3382967"},{"key":"e_1_3_4_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445315"},{"key":"e_1_3_4_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_4_73_2","unstructured":"RStudio Team. 2020. RStudio: Integrated Development Environment for R. Retrieved March 29 2022 from http:\/\/www.rstudio.com\/."},{"key":"e_1_3_4_74_2","doi-asserted-by":"publisher","DOI":"10.55612\/s-5002-019-002"},{"key":"e_1_3_4_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534128"},{"key":"e_1_3_4_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584066"},{"key":"e_1_3_4_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_4_78_2","volume-title":"International Conference on Learning Representations (ICLR) Workshop Track Proceedings","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2014. Deep inside convolutional networks: Visualising image classification models and saliency maps. In International Conference on Learning Representations (ICLR) Workshop Track Proceedings."},{"key":"e_1_3_4_79_2","unstructured":"Statens Naturhistoriske Museum et al. 2022. Danmarks svampeatlas. https:\/\/svampe.databasen.org\/ Accessed March 29 2022."},{"key":"e_1_3_4_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450613.3456817"},{"key":"e_1_3_4_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511163"},{"key":"e_1_3_4_82_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103404"},{"key":"e_1_3_4_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450650"},{"key":"e_1_3_4_84_2","unstructured":"Mengjiao Yang and Been Kim. 2019. Benchmarking attribution methods with relative feature importance. arXiv:1907.09701 [cs stat]. Retrieved from http:\/\/arxiv.org\/abs\/1907.09701"},{"key":"e_1_3_4_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517791"},{"key":"e_1_3_4_86_2","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372852"}],"container-title":["ACM Transactions on Interactive Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665647","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3665647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:04Z","timestamp":1750291564000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665647"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,2]]},"references-count":85,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1145\/3665647"],"URL":"https:\/\/doi.org\/10.1145\/3665647","relation":{},"ISSN":["2160-6455","2160-6463"],"issn-type":[{"value":"2160-6455","type":"print"},{"value":"2160-6463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,2]]},"assertion":[{"value":"2023-05-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}