{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T23:20:44Z","timestamp":1787959244382,"version":"build-2784847793"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032083166","type":"print"},{"value":"9783032083173","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    This paper introduces Multi-Output LOcal Narrative Explanation (\n                    <jats:sc>MOLONE<\/jats:sc>\n                    ), a novel comparative explanation method designed to enhance preference selection in human-in-the-loop Preference Bayesian optimization (PBO). The preference elicitation in PBO is a non-trivial task because it involves navigating implicit trade-offs between vector-valued outcomes, subjective priorities of decision-makers, and decision-makers\u2019 uncertainty in preference selection. Existing explainable AI (XAI) methods for BO primarily focus on input feature importance, neglecting the crucial role of outputs (objectives) in human preference elicitation.\n                    <jats:sc>MOLONE<\/jats:sc>\n                    addresses this gap by providing explanations that highlight both input and output importance, enabling decision-makers to understand the trade-offs between competing objectives and make more informed preference selections.\n                    <jats:sc>MOLONE<\/jats:sc>\n                    focuses on local explanations, comparing the importance of input features and outcomes across candidate samples within a local neighborhood of the search space, thus capturing nuanced differences relevant to preference-based decision-making. We evaluate\n                    <jats:sc>MOLONE<\/jats:sc>\n                    within a PBO framework using benchmark multi-objective optimization functions, demonstrating its effectiveness in improving convergence compared to noisy preference selections. Furthermore, a user study confirms that\n                    <jats:sc>MOLONE<\/jats:sc>\n                    significantly accelerates convergence in human-in-the-loop scenarios by facilitating more efficient identification of preferred options.\n                  <\/jats:p>","DOI":"10.1007\/978-3-032-08317-3_7","type":"book-chapter","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T03:36:54Z","timestamp":1760153814000},"page":"139-161","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Comparative Explanations: Explanation Guided Decision Making for\u00a0Human-in-the-Loop Preference Selection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0258-2270","authenticated-orcid":false,"given":"Tanmay","family":"Chakraborty","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9755-6639","authenticated-orcid":false,"given":"Christian","family":"Wirth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6776-3868","authenticated-orcid":false,"given":"Christin","family":"Seifert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"7_CR1","unstructured":"Adachi, M., et al.: Looping in the human: collaborative and explainable Bayesian optimization. In: AISTATS (2024)"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Arora, S., Pruthi, D., Sadeh, N., Cohen, W.W., Lipton, Z.C., Neubig, G.: Explain, edit, and understand: rethinking user study design for evaluating model explanations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 5277\u20135285 (2022)","DOI":"10.1609\/aaai.v36i5.20464"},{"key":"7_CR3","unstructured":"Bakshy, E., et al.: Ae: a domain-agnostic platform for adaptive experimentation. In: Conference on Neural Information Processing Systems, pp.\u00a01\u20138 (2018)"},{"key":"7_CR4","unstructured":"Balandat, M., et al.: Botorch: a framework for efficient monte-carlo bayesian optimization. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems. vol.\u00a033, pp. 21524\u201321538. Curran Associates, Inc. (2020). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/f5b1b89d98b7286673128a5fb112cb9a-Paper.pdf"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Cabitza, F., Natali, C., Famiglini, L., Campagner, A., Caccavella, V., Gallazzi, E.: Never tell me the odds: Investigating pro-hoc explanations in medical decision making. Artif. Intell. Med. 150, 102819 (2024)","DOI":"10.1016\/j.artmed.2024.102819"},{"key":"7_CR6","unstructured":"Chakraborty, T., Seifert, C., Wirth, C.: Explainable Bayesian optimization. arXiv preprint arXiv:2401.13334 (2024)"},{"key":"7_CR7","doi-asserted-by":"publisher","unstructured":"Chakraborty, T., Wirth, C., Seifert, C.: Post-hoc rule based explanations for black box Bayesian optimization. In: Nowaczyk, S., et al. (eds.) European Conference on Artificial Intelligence, pp. 320\u2013337. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-50396-2_18","DOI":"10.1007\/978-3-031-50396-2_18"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Chau, S.L., Muandet, K., Sejdinovic, D.: Explaining the uncertain: Stochastic shapley values for gaussian process models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.52202\/075280-2209"},{"key":"7_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/978-3-540-31880-4_11","volume-title":"Evolutionary Multi-Criterion Optimization","author":"K Deb","year":"2005","unstructured":"Deb, K., Gupta, H.: Searching for robust pareto-optimal solutions in multi-objective optimization. In: Coello Coello, C.A., Hern\u00e1ndez Aguirre, A., Zitzler, E. (eds.) EMO 2005. LNCS, vol. 3410, pp. 150\u2013164. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/978-3-540-31880-4_11"},{"key":"7_CR10","unstructured":"Dinu, J., Bigham, J., Zico\u00a0Kolter, J.: Challenging common interpretability assumptions in feature attribution explanations. In: NeurIPS Workshop: ML Retrospectives, Surveys & Meta-Analyses (ML-RSA) (2020)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Frazier, P.I., Wang, J.: Bayesian optimization for materials design. In: Information Science for Materials Discovery and Design, pp. 45\u201375 (2016)","DOI":"10.1007\/978-3-319-23871-5_3"},{"key":"7_CR12","series-title":"Geosystems Mathematics","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-319-71458-5_19","volume-title":"Spherical Sampling","author":"W Freeden","year":"2018","unstructured":"Freeden, W., Nashed, M.Z., Schreiner, M.: Applicabilities and applications. In: Spherical Sampling. GM, pp. 525\u2013531. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-71458-5_19"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Gan, W., Ji, Z., Liang, Y.: Acquisition functions in Bayesian optimization. In: 2021 2nd International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), pp. 129\u2013135. IEEE (2021)","DOI":"10.1109\/ICBASE53849.2021.00032"},{"key":"7_CR14","unstructured":"Gary, A.K.: Sources of Power: How People Make Decisions. Mass, Cambridge (1999)"},{"key":"7_CR15","unstructured":"Gonz\u00e1lez, J., Dai, Z., Damianou, A., Lawrence, N.D.: Preferential Bayesian optimization. In: International Conference on Machine Learning, pp. 1282\u20131291. PMLR (2017)"},{"issue":"3","key":"7_CR16","doi-asserted-by":"publisher","first-page":"1410","DOI":"10.1109\/TRO.2021.3133137","volume":"38","author":"DF Gordon","year":"2022","unstructured":"Gordon, D.F., McGreavy, C., Christou, A., Vijayakumar, S.: Human-in-the-loop optimization of exoskeleton assistance via online simulation of metabolic cost. IEEE Trans. Rob. 38(3), 1410\u20131429 (2022)","journal-title":"IEEE Trans. Rob."},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach. Part I: causes. Br. J. Philos. Sci. 56(4), 843\u2013887 (2005). http:\/\/www.jstor.org\/stable\/3541870","DOI":"10.1093\/bjps\/axi147"},{"issue":"4","key":"7_CR18","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1109\/MIS.2005.67","volume":"20","author":"RR Hoffman","year":"2005","unstructured":"Hoffman, R.R., Yates, J.F.: Decision making [human-centered computing]. IEEE Intell. Syst. 20(4), 76\u201383 (2005)","journal-title":"IEEE Intell. Syst."},{"key":"7_CR19","doi-asserted-by":"publisher","unstructured":"Iman, R.L.: Latin Hypercube Sampling. John Wiley and Sons, Ltd. (2014). https:\/\/doi.org\/10.1002\/9781118445112.stat03803, https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1002\/9781118445112.stat03803","DOI":"10.1002\/9781118445112.stat03803"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Jacovi, A., Swayamdipta, S., Ravfogel, S., Elazar, Y., Choi, Y., Goldberg, Y.: Contrastive explanations for model interpretability (2021). https:\/\/arxiv.org\/abs\/2103.01378","DOI":"10.18653\/v1\/2021.emnlp-main.120"},{"issue":"26","key":"7_CR21","doi-asserted-by":"publisher","first-page":"10975","DOI":"10.1039\/D2NR07147A","volume":"15","author":"Y Jin","year":"2023","unstructured":"Jin, Y., Kumar, P.V.: Bayesian optimisation for efficient material discovery: a mini review. Nanoscale 15(26), 10975\u201310984 (2023)","journal-title":"Nanoscale"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Jones, E.E., Davis, K.E.: From acts to dispositions the attribution process in person perception1. Adv. Exp. Soc. Psychol. 2, 219\u2013266 (1965). https:\/\/api.semanticscholar.org\/CorpusID:144754193","DOI":"10.1016\/S0065-2601(08)60107-0"},{"issue":"7","key":"7_CR23","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1109\/TSMC.1979.4310245","volume":"9","author":"RL Keeney","year":"1979","unstructured":"Keeney, R.L., Raiffa, H., Rajala, D.W.: Decisions with multiple objectives: preferences and value trade-offs. IEEE Trans. Syst. Man Cybern. 9(7), 403\u2013403 (1979). https:\/\/doi.org\/10.1109\/TSMC.1979.4310245","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"7_CR24","unstructured":"Lin, Z.J., Astudillo, R., Frazier, P., Bakshy, E.: Preference exploration for efficient bayesian optimization with multiple outcomes. In: International Conference on Artificial Intelligence and Statistics, pp. 4235\u20134258. PMLR (2022)"},{"key":"7_CR25","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":"7_CR26","doi-asserted-by":"crossref","unstructured":"Miller, T.: Contrastive explanation: a structural-model approach. Knowl. Eng. Rev. 36, e14 (2021)","DOI":"10.1017\/S0269888921000102"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Miller, T.: Explainable AI is dead, long live explainable AI! Hypothesis-driven decision support using evaluative AI. In: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, pp. 333\u2013342 (2023)","DOI":"10.1145\/3593013.3594001"},{"issue":"6","key":"7_CR28","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1108\/00251749510087605","volume":"33","author":"J Nicholls","year":"1995","unstructured":"Nicholls, J.: The mcc decision matrix: a tool for applying strategic logic toeveryday activity. Manag. Decis. 33(6), 4\u201310 (1995)","journal-title":"Manag. Decis."},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Rasmussen, C.E., Williams, C.K.: Gaussian Processes for Machine Learning, ser. Adaptive Computation and Machine Learning, vol. 38, pp. 715\u2013719. MIT Press, Cambridge (2006)","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"7_CR30","unstructured":"Rodemann, J., et al.: Explaining Bayesian optimization by Shapley values facilitates human-AI collaboration. arXiv preprint arXiv:2403.04629 (2024)"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Senoner, J., Schallmoser, S., Kratzwald, B., Feuerriegel, S., Netland, T.: Explainable AI improves task performance in human-AI collaboration. Sci. Rep. 14(1), 31150 (2024)","DOI":"10.1038\/s41598-024-82501-9"},{"issue":"1","key":"7_CR32","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","volume":"104","author":"B Shahriari","year":"2015","unstructured":"Shahriari, B., Swersky, K., Wang, Z., Adams, R.P., Freitas, N.: Taking the human out of the loop: a review of Bayesian optimization. Proc. IEEE 104(1), 148\u2013175 (2015)","journal-title":"Proc. IEEE"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Slovic, P.: The construction of preference. Am. Psychol. 50(5), 364 (1995)","DOI":"10.1037\/0003-066X.50.5.364"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Wang, K., Dowling, A.W.: Bayesian optimization for chemical products and functional materials. Curr. Opin. Chem. Eng. 36, 100728 (2022)","DOI":"10.1016\/j.coche.2021.100728"},{"issue":"10","key":"7_CR35","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1016\/j.ress.2007.06.003","volume":"93","author":"C Xu","year":"2008","unstructured":"Xu, C., Gertner, G.Z.: Uncertainty and sensitivity analysis for models with correlated parameters. Reliab. Eng. Syst. Saf. 93(10), 1563\u20131573 (2008)","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"7_CR36","doi-asserted-by":"publisher","first-page":"1987","DOI":"10.1109\/TNSRE.2021.3113636","volume":"29","author":"Z Zhao","year":"2021","unstructured":"Zhao, Z., et al.: Optimization of spinal cord stimulation using Bayesian preference learning and its validation. IEEE Trans. Neural Syst. Rehabil. Eng. 29, 1987\u20131997 (2021)","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"7_CR37","unstructured":"Zhou, H., Ma, X., Blaschko, M.B.: A corrected expected improvement acquisition function under noisy observations. In: Yan\u0131ko\u011flu, B., Buntine, W. (eds.) Proceedings of the 15th Asian Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0222, pp. 1747\u20131762. PMLR (2024)"},{"issue":"2","key":"7_CR38","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1162\/106365600568202","volume":"8","author":"E Zitzler","year":"2000","unstructured":"Zitzler, E., Deb, K., Thiele, L.: Comparison of multiobjective evolutionary algorithms: empirical results. Evol. Comput. 8(2), 173\u2013195 (2000). https:\/\/doi.org\/10.1162\/106365600568202","journal-title":"Evol. Comput."}],"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\/978-3-032-08317-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T17:13:57Z","timestamp":1787159637000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-08317-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"ISBN":["9783032083166","9783032083173"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-08317-3_7","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"12 October 2025","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":"Istanbul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"T\u00fcrkiye","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"xai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/xaiworldconference.com\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}