{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T00:25:27Z","timestamp":1773447927781,"version":"3.50.1"},"reference-count":82,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T00:00:00Z","timestamp":1746144000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"ANR JCJC FAbLe","award":["grant no. ANR-19-CE23-0019-01"],"award-info":[{"award-number":["grant no. ANR-19-CE23-0019-01"]}]},{"name":"Carlsberg Foundation","award":["grant CF21-0159"],"award-info":[{"award-number":["grant CF21-0159"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Hum.-Comput. Interact."],"published-print":{"date-parts":[[2025,5,2]]},"abstract":"<jats:p>Local explainability, an important sub-field of eXplainable AI, focuses on describing the decisions of AI models for individual use cases by providing the underlying relationships between a model's inputs and outputs. While the machine learning community has made substantial progress in improving explanation accuracy and completeness, these explanations are rarely evaluated by the final users. In this paper, we evaluate the impact of various explanation and representation techniques on users' comprehension and confidence. Through a user study on two different domains, we assessed three commonly used local explanation techniques\u2014feature-attribution, rule-based, and counterfactual\u2014and explored how their visual representation\u2014graphical or text-based\u2014influences users' comprehension and trust. Our results show that the choice of explanation technique primarily affects user comprehension, whereas the graphical representation impacts user confidence.<\/jats:p>","DOI":"10.1145\/3711011","type":"journal-article","created":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T01:35:05Z","timestamp":1746236105000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Impact of Explanation Techniques and Representations on Users' Comprehension and Confidence in Explainable AI"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6824-5010","authenticated-orcid":false,"given":"Julien","family":"Delaunay","sequence":"first","affiliation":[{"name":"Top Health Tech, Barcelona, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0241-5379","authenticated-orcid":false,"given":"Luis","family":"Gal\u00e1rraga","sequence":"additional","affiliation":[{"name":"Inria \/ IRISA, Rennes, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2739-5850","authenticated-orcid":false,"given":"Christine","family":"Largouet","sequence":"additional","affiliation":[{"name":"Institut Agro \/ IRISA, Rennes, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5106-7692","authenticated-orcid":false,"given":"Niels","family":"van Berkel","sequence":"additional","affiliation":[{"name":"Aalborg University, Aalborg, Denmark"}]}],"member":"320","published-online":{"date-parts":[[2025,5,2]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"e_1_2_1_2_1","volume-title":"Gilbert","author":"Alikhademi Kiana","year":"2021","unstructured":"Kiana Alikhademi, Brianna Richardson, Emma Drobina, and Juan E. Gilbert. 2021. Can Explainable AI Explain Unfairness? A Framework for Evaluating Explainable AI. arXiv:2106.07483 https:\/\/arxiv.org\/abs\/2106.07483"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01332--6"},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (Montreal QC, Canada) (AAMAS '19)","author":"Anjomshoae Sule","year":"2019","unstructured":"Sule Anjomshoae, Amro Najjar, Davide Calvaresi, and Kary Fr\u00e4mling. 2019. Explainable Agents and Robots: Results from a Systematic Literature Review. In Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (Montreal QC, Canada) (AAMAS '19). International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC, 1078--1088. https:\/\/www.ifaamas.org\/Proceedings\/aamas2019\/pdfs\/p1078.pdf"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-022-09324--9"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579460"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-020-09270--4"},{"key":"e_1_2_1_8_1","unstructured":"Francesco Bodria Fosca Giannotti Riccardo Guidotti Francesca Naretto Dino Pedreschi and Salvatore Rinzivillo. 2021. Benchmarking and Survey of Explanation Methods for Black Box Models. arXiv:2102.13076 https:\/\/arxiv.org\/abs\/2102.13076"},{"key":"e_1_2_1_9_1","volume-title":"Cooperation and Prosocial Behaviour","author":"Boon S","unstructured":"S Boon and J Holmes. 1991. The Dynamics of Interpersonal Trust: Resolving Uncertainity in the Face of Risk. In Cooperation and Prosocial Behaviour. Cambridge University Press, Cambridge, 190--211. https:\/\/www.scienceopen.com\/document?vid=f92a0587--18fc-4e40-b561--5ee691c53fc9"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385994"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1177\/0093854808326545"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3399\/bjgp18X695213"},{"key":"e_1_2_1_13_1","volume-title":"Explainable Artificial Intelligence","author":"Chaushi Blerta Abazi","unstructured":"Blerta Abazi Chaushi, Besnik Selimi, Agron Chaushi, and Marika Apostolova. 2023. Explainable Artificial Intelligence in Education: A Comprehensive Review. In Explainable Artificial Intelligence. Springer Nature Switzerland, Cham, 48--71. https:\/\/link.springer.com\/chapter\/10.1007\/978--3-031--44067-0_3"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300789"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450644"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1177\/0963721409359277"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3710946"},{"key":"e_1_2_1_18_1","unstructured":"Luca Deck Astrid Schom\u00e4cker Timo Speith Jakob Sch\u00f6ffer Lena K\u00e4stner and Niklas K\u00fchl. 2024. Mapping the Potential of Explainable AI for Fairness Along the AI Lifecycle. arXiv:2404.18736 https:\/\/arxiv.org\/abs\/2404.18736"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3417461"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557489"},{"key":"e_1_2_1_21_1","volume-title":"CHI 23","author":"Delaunay Julien","year":"2023","unstructured":"Julien Delaunay, Luis Gal\u00e1rraga, Christine Largou\u00ebt, and Niels van Berkel. 2023. Adaptation of AI Explanations to Users' Roles. 7 pages. https:\/\/vbn.aau.dk\/en\/publications\/adaptation-of-ai-explanations-to-users-roles 2023 ACM CHI Conference on Human Factors in Computing Systems, CHI 23 ; Conference date: 23-04--2023 Through 28-04--2023."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534647"},{"key":"e_1_2_1_23_1","unstructured":"Finale Doshi-Velez and Been Kim. 2017. Towards A Rigorous Science of Interpretable Machine Learning. https:\/\/arxiv.org\/abs\/1702.08608"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00831--6"},{"key":"e_1_2_1_26_1","unstructured":"Riccardo Guidotti Anna Monreale Salvatore Ruggieri Dino Pedreschi Franco Turini and Fosca Giannotti. 2018. Local Rule-Based Explanations of Black Box Decision Systems. https:\/\/api.semanticscholar.org\/CorpusID:44063479"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236009"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3301275.3308446"},{"key":"e_1_2_1_29_1","unstructured":"Joseph Hair William Black Barry Babin and Rolph Anderson. 2013. Multivariate Data Analysis. Pearson Education Limited Bagsvaerd Denmark. https:\/\/books.google.es\/books?id=VvXZnQEACAAJ"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.491"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2019.2904558"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.22295"},{"key":"e_1_2_1_33_1","unstructured":"Alon Jacovi. 2023. Trends in Explainable AI (XAI) Literature. arXiv:2301.05433 https:\/\/arxiv.org\/abs\/2301.05433"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01576"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/VLHCC.2013.6645235"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-022-01441-y"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610206"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939874"},{"key":"e_1_2_1_39_1","volume-title":"Anna De Liddo, and Enrico Motta","author":"Larasati Retno","year":"2020","unstructured":"Retno Larasati, Anna De Liddo, and Enrico Motta. 2020. The Effect of Explanation Styles on User's Trust. In Proceedings of the Workshop on Explainable Smart Systems for Algorithmic Transparency in Emerging Technologies co-located with 25th International Conference on Intelligent User Interfaces (IUI 2020), Cagliari, Italy, March 17, 2020 (CEUR Workshop Proceedings, Vol. 2582). CEUR-WS.org, Aachen, Germany. http:\/\/ceur-ws.org\/Vol-2582\/paper6.pdf"},{"key":"e_1_2_1_40_1","unstructured":"Jeff Larson Julia Angwin Lauren Kirchner and Surya Mattu. 2016. How We Analyzed the COMPAS Recidivism Algorithm \u2014 propublica.org. https:\/\/www.propublica.org\/article\/how-we-analyzed-the-compas-recidivism-algorithm"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3--319--91473--2_9"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3233231"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295230"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467265"},{"key":"e_1_2_1_45_1","volume-title":"American Conference for Irish Studies 1 (01","author":"Madsen Maria","year":"2000","unstructured":"Maria Madsen and Shirley Gregor. 2000. Measuring human-computer trust. American Conference for Irish Studies 1 (01 2000)."},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581575"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104344"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0043158"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387166"},{"key":"e_1_2_1_51_1","unstructured":"Christoph Molnar. 2018. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. Independently published. https:\/\/christophm.github.io\/interpretable-ml-book\/"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372850"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490100.3516481"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3686922"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445315"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375850"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.54476\/ioer-imrj\/86523"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_2_1_59_1","doi-asserted-by":"crossref","unstructured":"Marco Tulio Ribeiro Sameer Singh and Carlos Guestrin. 2018. Anchors: high-precision model-agnostic explanations. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence (New Orleans Louisiana USA) (AAAI'18\/IAAI'18\/EAAI'18). AAAI Press Washington D.C. USA Article 187 9 pages. https:\/\/aaai.org\/papers\/11491-anchors-high-precision-model-agnostic-explanations\/","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"e_1_2_1_60_1","volume-title":"Proceedings of the International Conference on Intelligent User Interfaces (CEUR Workshop Proceedings). CEUR-WS.org","author":"Mireia","year":"2019","unstructured":"Mireia Ribera and \u00c0gata Lapedriza. 2019. Can we do better explanations? A proposal of user-centered explainable AI. In Proceedings of the International Conference on Intelligent User Interfaces (CEUR Workshop Proceedings). CEUR-WS.org, Aachen, Germany, 7. http:\/\/ceur-ws.org\/Vol-2327\/IUI19WS-ExSS2019--12.pdf"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.306"},{"key":"e_1_2_1_62_1","volume-title":"Lisa Fiedler, Peizhu Qian, Vaibhav Unhelkar, Tina Seidel, Gjergji Kasneci, and Enkelejda Kasneci.","author":"Rong Yao","year":"2023","unstructured":"Yao Rong, Tobias Leemann, Thai trang Nguyen, Lisa Fiedler, Peizhu Qian, Vaibhav Unhelkar, Tina Seidel, Gjergji Kasneci, and Enkelejda Kasneci. 2023. Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations. arXiv:2210.11584"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3301275.3302308"},{"key":"e_1_2_1_65_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning -","volume":"70","author":"Shrikumar Avanti","year":"2017","unstructured":"Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. 2017. Learning important features through propagating activation differences. In Proceedings of the 34th International Conference on Machine Learning - Volume 70 (Sydney, NSW, Australia) (ICML'17). JMLR.org, Brookline, Massachusetts, USA, 3145--3153."},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20464"},{"key":"e_1_2_1_67_1","volume-title":"And Dataset. In Proceedings of the International Conference on Learning Representations. OpenReview.net, 23","author":"Sixt Leon","year":"2022","unstructured":"Leon Sixt, Martin Schuessler, Oana-Iuliana Popescu, Philipp Wei\u00df, and Tim Landgraf. 2022. Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset. In Proceedings of the International Conference on Learning Representations. OpenReview.net, 23. https:\/\/openreview.net\/forum?id=v6s3HVjPerv"},{"key":"e_1_2_1_68_1","volume-title":"Soares and Plamen Angelov","author":"Eduardo","year":"2019","unstructured":"Eduardo A. Soares and Plamen Angelov. 2019. Fair-by-design explainable models for prediction of recidivism. CoRR abs\/1910.02043 (2019), 5. http:\/\/arxiv.org\/abs\/1910.02043"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3306024"},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511160"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-021-09301--8"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445365"},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2024.103359"},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103404"},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3063289"},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450650"},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519266"},{"key":"e_1_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308532.3329441"},{"key":"e_1_2_1_79_1","volume-title":"Weld and Gagan Bansal","author":"Daniel","year":"2018","unstructured":"Daniel S. Weld and Gagan Bansal. 2018. Intelligible Artificial Intelligence. CoRR (2018), 8. http:\/\/arxiv.org\/abs\/1803.04263"},{"key":"e_1_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934619"},{"key":"e_1_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.541"},{"key":"e_1_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3546930.3547502"}],"container-title":["Proceedings of the ACM on Human-Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711011","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711011","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:59:50Z","timestamp":1755737990000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711011"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,2]]},"references-count":82,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,5,2]]}},"alternative-id":["10.1145\/3711011"],"URL":"https:\/\/doi.org\/10.1145\/3711011","relation":{},"ISSN":["2573-0142"],"issn-type":[{"value":"2573-0142","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,2]]},"assertion":[{"value":"2025-05-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}