TECHNOLOGY AND CODE article
Front. Comput. Sci.
Sec. Human-Media Interaction
Generation and Evaluation of Adaptive Explanations Based on Dynamic Partner-Modeling and Non-Stationary Decision Making
Provisionally accepted
- Bielefeld University, Bielefeld, Germany
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Adapting to the addressee is crucial for successful explanations, yet poses significant challenges for dialogsystems. We adopt the approach of treating explanation generation as a non-stationary decision process, where the optimal strategy varies according to changing beliefs about the explainee and the interaction context. In this paper we address the questions of (1) how to track the interaction context and the relevant adaptation parameters in a formally defined computational partner model, and (2) how to utilize this model in the dynamically adjusted, rational decision process that determines the currently best explanation strategy. We propose a Bayesian inference-based approach to continuously update the partner model based on user feedback, and a non-stationary Markov Decision Process to adjust decision-making based on the partner model values. We evaluate an implementation of this framework in an online user-study showing the positive effects of a broader partner model. The results show that an adapted explanation results in a higher level of user understanding, highlighting the potential of our approach to improve current dialogsystems.
Keywords: adaptivity, Dynamic Bayesian network, Explainability, HumanEvaluation, Non-stationary Decision Process, Partner Models, user study
Received: 17 Dec 2025; Accepted: 12 Jan 2026.
Copyright: © 2026 Robrecht, Kowalski and Kopp. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Amelie S Robrecht
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.