{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:33:00Z","timestamp":1763058780933,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031188428"},{"type":"electronic","value":"9783031188435"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":282,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>A user receiving an explanation for outcomes produced by an artificially intelligent system expects that it satisfies the key property of <jats:italic>descriptive accuracy<\/jats:italic> (DA), i.e. that the explanation contents are in correspondence with the internal working of the system. Crucial as this property appears to be, it has been somehow overlooked in the XAI literature to date. To address this problem, we consider the questions of formalising DA and of analysing its satisfaction by explanation methods. We provide formal definitions of <jats:italic>naive, structural<\/jats:italic> and <jats:italic>dialectical<\/jats:italic> DA, using the family of probabilistic classifiers as the context for our analysis. We evaluate the satisfaction of our given notions of DA by several explanation methods, amounting to two popular feature-attribution methods from the literature and a novel form of explanation that we propose and complement our analysis with experiments carried out on a varied selection of concrete probabilistic classifiers.<\/jats:p>","DOI":"10.1007\/978-3-031-18843-5_19","type":"book-chapter","created":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T07:03:42Z","timestamp":1665731022000},"page":"279-294","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Descriptive Accuracy in\u00a0Explanations: The Case of\u00a0Probabilistic Classifiers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2964-4638","authenticated-orcid":false,"given":"Emanuele","family":"Albini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5323-7739","authenticated-orcid":false,"given":"Antonio","family":"Rago","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5439-9561","authenticated-orcid":false,"given":"Pietro","family":"Baroni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8194-1459","authenticated-orcid":false,"given":"Francesca","family":"Toni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Alvarez-Melis, D., Jaakkola, T.S.: A causal framework for explaining the predictions of black-box sequence-to-sequence models. In: EMNLP (2017)","DOI":"10.18653\/v1\/D17-1042"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Bielza, C., Larra\u00f1aga, P.: Discrete Bayesian network classifiers: a survey. ACM Comput. Surv. 47(1), 5:1\u20135:43 (2014)","DOI":"10.1145\/2576868"},{"key":"19_CR3","unstructured":"BNlearn: Bayesian network repository - an R package for Bayesian network learning and inference (2020). https:\/\/www.bnlearn.com\/bnrepository"},{"key":"19_CR4","unstructured":"Club, L.: Lending Club Loans (2019). https:\/\/kaggle.com\/wordsforthewise\/lending-club"},{"key":"19_CR5","unstructured":"FICO Community: Explainable Machine Learning Challenge (2019). https:\/\/community.fico.com\/s\/explainable-machine-learning-challenge"},{"key":"19_CR6","unstructured":"Dhurandhar, A., et al.: Explanations based on the missing: towards contrastive explanations with pertinent negatives. In: NeurIPS (2018)"},{"issue":"2\u20133","key":"19_CR7","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1023\/A:1007465528199","volume":"29","author":"N Friedman","year":"1997","unstructured":"Friedman, N., Geiger, D., Goldszmidt, M.: Bayesian network classifiers. Mach. Learn. 29(2\u20133), 131\u2013163 (1997). https:\/\/doi.org\/10.1023\/A:1007465528199","journal-title":"Mach. Learn."},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(5), 93:1\u201393:42 (2019)","DOI":"10.1145\/3236009"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Ignatiev, A., Narodytska, N., Marques-Silva, J.: Abduction-based explanations for machine learning models. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33011511"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Jacovi, A., Marasovic, A., Miller, T., Goldberg, Y.: Formalizing trust in artificial intelligence: Prerequisites, causes and goals of human trust in AI. In: FAccT (2021)","DOI":"10.1145\/3442188.3445923"},{"issue":"3","key":"19_CR11","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/S0167-7152(96)00140-X","volume":"33","author":"R Kelley Pace","year":"1997","unstructured":"Kelley Pace, R., Barry, R.: Sparse spatial autoregressions. Stat. Probab. Lett. 33(3), 291\u2013297 (1997)","journal-title":"Stat. Probab. Lett."},{"issue":"2","key":"19_CR12","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1017\/S026988890200019X","volume":"17","author":"C Lacave","year":"2002","unstructured":"Lacave, C., D\u00edez, F.J.: A review of explanation methods for Bayesian networks. Knowl. Eng. Rev. 17(2), 107\u2013127 (2002). https:\/\/doi.org\/10.1017\/S026988890200019X","journal-title":"Knowl. Eng. Rev."},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Lakkaraju, H., Kamar, E., Caruana, R., Leskovec, J.: Faithful and customizable explanations of black box models. In: AIES (2019)","DOI":"10.1145\/3306618.3314229"},{"issue":"1","key":"19_CR14","first-page":"137","volume":"62","author":"S Lipovetsky","year":"2020","unstructured":"Lipovetsky, S.: Let the evidence speak - using Bayesian thinking in law, medicine, ecology and other areas. Technometrics 62(1), 137\u2013138 (2020)","journal-title":"Technometrics"},{"key":"19_CR15","unstructured":"Lundberg, S.M., Lee, S.: A unified approach to interpreting model predictions. In: NeurIPS (2017)"},{"issue":"3","key":"19_CR16","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1145\/321033.321035","volume":"7","author":"ME Maron","year":"1960","unstructured":"Maron, M.E., Kuhns, J.L.: On relevance, probabilistic indexing and information retrieval. J. ACM 7(3), 216\u2013244 (1960)","journal-title":"J. ACM"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"McLachlan, S., Dube, K., Hitman, G.A., Fenton, N.E., Kyrimi, E.: Bayesian networks in healthcare: distribution by medical condition. Artif. Intell. Medicine 107, 101912 (2020)","DOI":"10.1016\/j.artmed.2020.101912"},{"key":"19_CR18","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1016\/j.neucom.2021.01.138","volume":"456","author":"B Mihaljevic","year":"2021","unstructured":"Mihaljevic, B., Bielza, C., Larra\u00f1aga, P.: Bayesian networks for interpretable machine learning and optimization. Neurocomputing 456, 648\u2013665 (2021)","journal-title":"Neurocomputing"},{"issue":"44","key":"19_CR19","doi-asserted-by":"publisher","first-page":"22071","DOI":"10.1073\/pnas.1900654116","volume":"116","author":"WJ Murdoch","year":"2019","unstructured":"Murdoch, W.J., Singh, C., Kumbier, K., Abbasi-Asl, R., Yu, B.: Definitions, methods, and applications in interpretable machine learning. Proc. Natl. Acad. Sci. 116(44), 22071\u201322080 (2019)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"19_CR20","volume-title":"Probabilistic Methods for Financial and Marketing Informatics","author":"RE Neapolitan","year":"2010","unstructured":"Neapolitan, R.E., Jiang, X.: Probabilistic Methods for Financial and Marketing Informatics. Elsevier, Amsterdam (2010)"},{"key":"19_CR21","volume-title":"Probabilistic Reasoning in Intelligent Systems - Networks of Plausible Inference","author":"J Pearl","year":"1989","unstructured":"Pearl, J.: Probabilistic Reasoning in Intelligent Systems - Networks of Plausible Inference. Morgan Kaufmann, Burlington (1989)"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Provan, G.M., Singh, M.: Learning Bayesian networks using feature selection. In: AISTATS (1995)","DOI":"10.1007\/978-1-4612-2404-4_28"},{"key":"19_CR23","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1007\/978-3-642-04174-7_17","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"J Read","year":"2009","unstructured":"Read, J., Pfahringer, B., Holmes, G., Frank, E.: Classifier chains for multi-label classification. In: Buntine, W., Grobelnik, M., Mladeni\u0107, D., Shawe-Taylor, J. (eds.) ECML PKDD 2009. LNCS (LNAI), vol. 5782, pp. 254\u2013269. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-04174-7_17"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: \u201cWhy should i trust you?\u201d: explaining the predictions of any classifier. In: ACM SIGKDD (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Shih, A., Choi, A., Darwiche, A.: A symbolic approach to explaining Bayesian network classifiers. In: IJCAI (2018)","DOI":"10.24963\/ijcai.2018\/708"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Sokol, K., Flach, P.A.: Explainability fact sheets: a framework for systematic assessment of explainable approaches. In: FAT* (2020)","DOI":"10.1145\/3351095.3372870"},{"key":"19_CR27","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/978-3-319-20807-7_8","volume-title":"Symbolic and Quantitative Approaches to Reasoning with Uncertainty","author":"ST Timmer","year":"2015","unstructured":"Timmer, S.T., Meyer, J.-J.C., Prakken, H., Renooij, S., Verheij, B.: Explaining Bayesian networks using argumentation. In: Destercke, S., Denoeux, T. (eds.) ECSQARU 2015. LNCS (LNAI), vol. 9161, pp. 83\u201392. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-20807-7_8"},{"key":"19_CR28","unstructured":"UCI, C.: Machine Learning Repository (2020). https:\/\/archive.ics.uci.edu\/ml\/datasets.php"},{"key":"19_CR29","unstructured":"Zaragoza, J.H., Sucar, L.E., Morales, E.F., Bielza, C., Larra\u00f1aga, P.: Bayesian chain classifiers for multidimensional classification. In: IJCAI (2011)"}],"container-title":["Lecture Notes in Computer Science","Scalable Uncertainty Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18843-5_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T07:10:07Z","timestamp":1665731407000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18843-5_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031188428","9783031188435"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18843-5_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SUM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Scalable Uncertainty Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Paris","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sum2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sum2022.sciencesconf.org\/","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":"25","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":"19","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":"4","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":"76% - 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":"2.1","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}