Abstract
The increasing applications of AI systems require personalized explanations for their behaviors to various stakeholders since the stakeholders may have various backgrounds. In general, a conversation between explainers and explainees not only allows explainers to obtain the explainees’ background, but also allows explainees to better understand the explanations. In this paper, we propose an approach for an explainer to communicate personalized explanations to an explainee through having consecutive conversations with the explainee. We prove that the conversation terminates due to the explainee’s justification of the initial claim as long as there exists an explanation for the initial claim that the explainee understands and the explainer is aware of.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
This property requires a so-called axiomatically appropriate constant specification.
References
Antoniad, A.M., et al.: Current challenges and future opportunities for XAI in machine learning-based clinical decision support systems: a systematic review. Appl. Sci. 11(11), 5088 (2021)
Artemov, S.: Explicit provability and constructive semantics. Bull. Symbolic Logic 7(1), 1–36 (2001)
Artemov, S., Fitting, M.: Justification Logic: Reasoning with Reasons. University Press, Cambridge (2019)
Artemov, S.N.: The ontology of justifications in the logical setting. Studia Logica 100(1–2), 17–30 (2012). https://doi.org/10.1007/s11225-012-9387-x, published online February 2012
Artemov, S.N., Nogina, E.: Introducing justification into epistemic logic. J. Log. Comput. 15(6), 1059–1073 (2005). https://doi.org/10.1093/logcom/exi053
Fitting, M.: The logic of proofs, semantically. APAL 132(1), 1–25 (2005). https://doi.org/10.1016/j.apal.2004.04.009
Hilton, D.J.: Conversational processes and causal explanation. Psychol. Bull. 107(1), 65 (1990)
Kuznets, R., Studer, T.: Justifications, ontology, and conservativity. In: Bolander, T., Braüner, T., Ghilardi, S., Moss, L. (eds.) Advances in Modal Logic, Volume 9, pp. 437–458. College Publications (2012)
Kuznets, R., Studer, T.: Logics of Proofs and Justifications. College Publications (2019)
Lehmann, E., Studer, T.: Subset models for justification logic. In: Iemhoff, R., Moortgat, M., de Queiroz, R. (eds.) WoLLIC 2019. LNCS, vol. 11541, pp. 433–449. Springer, Heidelberg (2019). https://doi.org/10.1007/978-3-662-59533-6_26
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)
Plaza, J.: Logics of public communications. Synthese 158(2), 165–179 (2007). https://doi.org/10.1007/s11229-007-9168-7
Tsai, C.H., Brusilovsky, P.: The effects of controllability and explainability in a social recommender system. User Model. User-Adap. Inter. 31(3), 591–627 (2021)
Xu, C., Wang, Y., Studer, T.: A logic of knowing why. Synthese 198, 1259–1285 (2021)
Acknowledgement
This work is financially supported by the Swiss National Science Foundation grant 200020_184625.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Luo, J., Studer, T., Dastani, M. (2023). Providing Personalized Explanations: A Conversational Approach. In: Herzig, A., Luo, J., Pardo, P. (eds) Logic and Argumentation. CLAR 2023. Lecture Notes in Computer Science(), vol 14156. Springer, Cham. https://doi.org/10.1007/978-3-031-40875-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-40875-5_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40874-8
Online ISBN: 978-3-031-40875-5
eBook Packages: Computer ScienceComputer Science (R0)