{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:08:22Z","timestamp":1782346102312,"version":"3.54.5"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031440663","type":"print"},{"value":"9783031440670","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44067-0_5","type":"book-chapter","created":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T06:02:33Z","timestamp":1697781753000},"page":"88-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Compare-xAI: Toward Unifying Functional Testing Methods for\u00a0Post-hoc XAI Algorithms into\u00a0a\u00a0Multi-dimensional Benchmark"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9038-9045","authenticated-orcid":false,"given":"Mohamed Karim","family":"Belaid","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2392-3169","authenticated-orcid":false,"given":"Richard","family":"Bornemann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0755-1772","authenticated-orcid":false,"given":"Maximilian","family":"Rabus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5036-8589","authenticated-orcid":false,"given":"Ralf","family":"Krestel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9944-4108","authenticated-orcid":false,"given":"Eyke","family":"H\u00fcllermeier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,21]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: Why should I trust you? Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135\u20131144 (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Dressel, J., Farid, H.: The accuracy, fairness, and limits of predicting recidivism. Sci. Advances 4(1), eaao5580 (2018)","DOI":"10.1126\/sciadv.aao5580"},{"issue":"3","key":"5_CR3","first-page":"50","volume":"38","author":"B Goodman","year":"2017","unstructured":"Goodman, B., Flaxman, S.: European union regulations on algorithmic decision-making and a \u201cright to explanation\u2019\u2019. AI Mag. 38(3), 50\u201357 (2017)","journal-title":"AI Mag."},{"key":"5_CR4","unstructured":"Sundararajan, M., Najmi, A.: The many Shapley values for model explanation. In: International Conference on Machine Learning, pp. 9269\u20139278. PMLR (2020)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Shapley, L.S.: Quota Solutions op N-person games1. Edited by Emil Artin and Marston Morse, p. 343 (1953)","DOI":"10.1515\/9781400881970-021"},{"issue":"3","key":"5_CR6","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/s10115-013-0679-x","volume":"41","author":"E \u0160trumbelj","year":"2014","unstructured":"\u0160trumbelj, E., Kononenko, I.: Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst. 41(3), 647\u2013665 (2014)","journal-title":"Knowl. Inf. Syst."},{"key":"5_CR7","unstructured":"Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"5_CR8","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319\u20133328. PMLR (2017)"},{"key":"5_CR9","unstructured":"Lundberg, S.M., Erion, G.G., Lee, S.-I.: Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888 (2018)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Staniak, M., Biecek, P.: Explanations of model predictions with live and breakdown packages. arXiv preprint arXiv:1804.01955 (2018)","DOI":"10.32614\/RJ-2018-072"},{"issue":"5","key":"5_CR11","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1207\/s15516709cog2605_1","volume":"26","author":"L Rozenblit","year":"2002","unstructured":"Rozenblit, L., Keil, F.: The misunderstood limits of folk science: an illusion of explanatory depth. Cogn. Sci. 26(5), 521\u2013562 (2002)","journal-title":"Cogn. Sci."},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Chromik, M., Eiband, M, Buchner, F., Kr\u00fcger, A., Butz, A.: I think I get your point, AI! the illusion of explanatory depth in explainable AI. In: 26th International Conference on Intelligent User Interfaces, pp. 307\u2013317 (2021)","DOI":"10.1145\/3397481.3450644"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Kaur, H., Nori, H., Jenkins, S., Caruana, R., Wallach, H., Vaughan, J.W.: Interpreting interpretability: understanding data scientists\u2019 use of interpretability tools for machine learning. In: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, pp. 1\u201314 (2020)","DOI":"10.1145\/3313831.3376219"},{"key":"5_CR14","unstructured":"Leavitt, M.L., Morcos, A.: Towards falsifiable interpretability research. arXiv preprint arXiv:2010.12016 (2020)"},{"key":"5_CR15","volume-title":"The Ethical Algorithm: The Science of Socially Aware Algorithm Design","author":"M Kearns","year":"2019","unstructured":"Kearns, M., Roth, A.: The Ethical Algorithm: The Science of Socially Aware Algorithm Design. Oxford University Press, Oxford (2019)"},{"key":"5_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","volume":"267","author":"T Miller","year":"2019","unstructured":"Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1\u201338 (2019)","journal-title":"Artif. Intell."},{"key":"5_CR17","volume-title":"Black-Box Testing: Techniques for Functional Testing of Software and Systems","author":"B Beizer","year":"1995","unstructured":"Beizer, B.: Black-Box Testing: Techniques for Functional Testing of Software and Systems. Wiley, Hoboken (1995)"},{"key":"5_CR18","unstructured":"LeCun, Y., Cortes, C., Burges, C.J.: MNIST handwritten digit database. ATT Labs (2010). https:\/\/yann.lecun.com\/exdb\/mnist"},{"key":"5_CR19","unstructured":"Covert, I., Lundberg, S.M., Lee, S.-I.: Understanding global feature contributions with additive importance measures. In: Advances in Neural Information Processing Systems, vol. 33, pp. 17212\u201317223 (2020)"},{"key":"5_CR20","unstructured":"Tsang, M., Rambhatla, S., Liu, Y.: How does this interaction affect me? Interpretable attribution for feature interactions. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6147\u20136159 (2020)"},{"key":"5_CR21","unstructured":"Elizabeth Kumar, I., Venkatasubramanian, S., Scheidegger, C., Friedler, S.: Problems with Shapley-value-based explanations as feature importance measures. In: International Conference on Machine Learning, pp. 5491\u20135500. PMLR (2020)"},{"key":"5_CR22","unstructured":"Mohseni, S., Zarei, N., Ragan, E.D.: A multidisciplinary survey and framework for design and evaluation of explainable AI systems. arXiv preprint arXiv:1811.11839 (2018)"},{"key":"5_CR23","unstructured":"Tsang, M., Enouen, J., Liu, Y.: Interpretable artificial intelligence through the lens of feature interaction. arXiv preprint arXiv:2103.03103 (2021)"},{"issue":"5","key":"5_CR24","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1424","volume":"11","author":"PP Angelov","year":"2021","unstructured":"Angelov, P.P., Soares, E.A., Jiang, R., Arnold, N.I., Atkinson, P.M.: Explainable artificial intelligence: an analytical review. Wiley Interdisc. Rev. Data Min. Knowl. Discov. 11(5), e1424 (2021)","journal-title":"Wiley Interdisc. Rev. Data Min. Knowl. Discov."},{"issue":"5","key":"5_CR25","doi-asserted-by":"publisher","first-page":"593","DOI":"10.3390\/electronics10050593","volume":"10","author":"J Zhou","year":"2021","unstructured":"Zhou, J., Gandomi, A.H., Chen, F., Holzinger, A.: Evaluating the quality of machine learning explanations: a survey on methods and metrics. Electronics 10(5), 593 (2021)","journal-title":"Electronics"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Rozemberczki, B., et al.: The Shapley value in machine learning. arXiv preprint arXiv:2202.05594 (2022)","DOI":"10.24963\/ijcai.2022\/778"},{"key":"5_CR27","unstructured":"Nauta, M., et al.: From anecdotal evidence to quantitative evaluation methods: a systematic review on evaluating explainable AI. arXiv preprint arXiv:2201.08164 (2022)"},{"key":"5_CR28","unstructured":"Molnar, C.: Interpretable machine learning. Lulu.com (2020)"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Sattarzadeh, S., Sudhakar, M., Plataniotis, K.N.: SVEA: a small-scale benchmark for validating the usability of post-hoc explainable AI solutions in image and signal recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4158\u20134167 (2021)","DOI":"10.1109\/ICCVW54120.2021.00462"},{"key":"5_CR30","unstructured":"Greydanus, S.: Scaling down deep learning. arXiv preprint arXiv:2011.14439 (2020)"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"DeYoung, J., et al.: Eraser: a benchmark to evaluate rationalized NLP models. arXiv preprint arXiv:1911.03429 (2019)","DOI":"10.18653\/v1\/2020.acl-main.408"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Mohseni, S., Block, J.E., Ragan, E.D.: Quantitative evaluation of machine learning explanations: a human-grounded benchmark. arXiv preprint arXiv:1801.05075 (2020)","DOI":"10.1145\/3397481.3450689"},{"key":"5_CR33","unstructured":"Liu, Y., Khandagale, S., White, C., Neiswanger, W.: Synthetic benchmarks for scientific research in explainable machine learning. arXiv preprint arXiv:2106.12543 (2021)"},{"key":"5_CR34","unstructured":"Sharma, A., Melnikov, V., H\u00fcllermeier, E., Wehrheim, H.: Property-driven black-box testing of numeric functions. Softw. Eng. 2023 (2023)"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Chrysostomou, G., Aletras, N.: Improving the faithfulness of attention-based explanations with task-specific information for text classification. arXiv preprint arXiv:2105.02657 (2021)","DOI":"10.18653\/v1\/2021.acl-long.40"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Hamamoto, M., Egi, M.: Model-agnostic ensemble-based explanation correction leveraging Rashomon effect. In: 2021 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 01\u201308. IEEE (2021)","DOI":"10.1109\/SSCI50451.2021.9659874"},{"key":"5_CR37","unstructured":"Hameed, I., et al.: Based-XAI: breaking ablation studies down for explainable artificial intelligence. arXiv preprint arXiv:2207.05566 (2022)"},{"key":"5_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103428","volume":"291","author":"R Guidotti","year":"2021","unstructured":"Guidotti, R.: Evaluating local explanation methods on ground truth. Artif. Intell. 291, 103428 (2021)","journal-title":"Artif. Intell."},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Lin, Y.-S., Lee, W.-C., Berkay Celik, Z.: What do you see? Evaluation of explainable artificial intelligence (XAI) interpretability through neural backdoors. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1027\u20131035 (2021)","DOI":"10.1145\/3447548.3467213"},{"issue":"34","key":"5_CR40","first-page":"1","volume":"24","author":"A Hedstr\u00f6m","year":"2023","unstructured":"Hedstr\u00f6m, A., et al.: An explainable AI toolkit for responsible evaluation of neural network explanations and beyond. J. Mach. Learn. Res. 24(34), 1\u201311 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR41","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.inffus.2021.11.008","volume":"81","author":"L Arras","year":"2022","unstructured":"Arras, L., Osman, A., Samek, W.: CLEVR-XAI: a benchmark dataset for the ground truth evaluation of neural network explanations. Inf. Fusion 81, 14\u201340 (2022)","journal-title":"Inf. Fusion"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Du, M., Liu, N., Yang, F., Ji, S., Hu, X.: On attribution of recurrent neural network predictions via additive decomposition. In: The World Wide Web Conference, pp. 383\u2013393 (2019)","DOI":"10.1145\/3308558.3313545"},{"key":"5_CR43","unstructured":"Agarwal, C., et al.: OpenXAI: towards a transparent evaluation of model explanations. In: Advances in Neural Information Processing Systems, vol. 35, pp. 15784\u201315799 (2022)"},{"key":"5_CR44","unstructured":"Plumb, G., Molitor, D., Talwalkar, A.S.: Model agnostic supervised local explanations. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Owen, G.: Multilinear extensions of games. Manag. Sci. 18(5-part-2), 64\u201379 (1972)","DOI":"10.1287\/mnsc.18.5.64"},{"key":"5_CR46","unstructured":"Sundararajan, M., Dhamdhere, K., Agarwal, A.: The Shapley Taylor interaction index. In: International Conference on Machine Learning, pp. 9259\u20139268. PMLR (2020)"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Ghorbani, A., Abid, A., Zou, J.: Interpretation of neural networks is fragile. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3681\u20133688 (2019)","DOI":"10.1609\/aaai.v33i01.33013681"},{"key":"5_CR48","unstructured":"Janzing, D., Minorics, L., Bl\u00f6baum, P.: Feature relevance quantification in explainable AI: a causal problem. In: International Conference on Artificial Intelligence and Statistics, pp. 2907\u20132916. PMLR (2020)"},{"issue":"6","key":"5_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11222-021-10057-z","volume":"31","author":"G Hooker","year":"2021","unstructured":"Hooker, G., Mentch, L., Zhou, S.: Unrestricted permutation forces extrapolation: variable importance requires at least one more model, or there is no free variable importance. Stat. Comput. 31(6), 1\u201316 (2021)","journal-title":"Stat. Comput."},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"Lakkaraju, H., Kamar, E, Caruana, R., Leskovec, J.: Faithful and customizable explanations of black box models. In: Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society, pp. 131\u2013138 (2019)","DOI":"10.1145\/3306618.3314229"},{"key":"5_CR51","unstructured":"Melis, D.A., Jaakkola, T.: Towards robust interpretability with self-explaining neural networks. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Lakkaraju, H., Bastani, O.: \u201cHow do I fool you?\u201d manipulating user trust via misleading black box explanations. In: Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society, pp. 79\u201385 (2020)","DOI":"10.1145\/3375627.3375833"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Mollas, I., Bassiliades, N., Tsoumakas, G.: Altruist: argumentative explanations through local interpretations of predictive models. In: Proceedings of the 12th Hellenic Conference on Artificial Intelligence, pp. 1\u201310 (2022)","DOI":"10.1145\/3549737.3549762"},{"issue":"1","key":"5_CR54","first-page":"3","volume":"9","author":"J Larson","year":"2016","unstructured":"Larson, J., Mattu, S., Kirchner, L., Angwin, J.: How we analyzed the COMPAS recidivism algorithm. ProPublica 9(1), 3 (2016)","journal-title":"ProPublica"},{"key":"5_CR55","unstructured":"Jeyakumar, J.V., Noor, J., Cheng, Y.-H., Garcia, L., Srivastava, M.: How can I explain this to you? An empirical study of deep neural network explanation methods. In: Advances in Neural Information Processing Systems, vol. 33, pp. 4211\u20134222 (2020)"},{"key":"5_CR56","unstructured":"Harris, C., Pymar, R., Rowat, C.: Joint Shapley values: a measure of joint feature importance. arXiv preprint arXiv:2107.11357 (2021)"}],"container-title":["Communications in Computer and Information Science","Explainable Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44067-0_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:04:01Z","timestamp":1707804241000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44067-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031440663","9783031440670"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44067-0_5","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"21 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"xAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"World Conference on Explainable Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"xai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/xaiworldconference.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"220","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"94","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"43% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}