English

On Interactive Explanations as Non-Monotonic Reasoning

Artificial Intelligence 2022-08-02 v1

Abstract

Recent work shows issues of consistency with explanations, with methods generating local explanations that seem reasonable instance-wise, but that are inconsistent across instances. This suggests not only that instance-wise explanations can be unreliable, but mainly that, when interacting with a system via multiple inputs, a user may actually lose confidence in the system. To better analyse this issue, in this work we treat explanations as objects that can be subject to reasoning and present a formal model of the interactive scenario between user and system, via sequences of inputs, outputs, and explanations. We argue that explanations can be thought of as committing to some model behaviour (even if only prima facie), suggesting a form of entailment, which, we argue, should be thought of as non-monotonic. This allows: 1) to solve some considered inconsistencies in explanation, such as via a specificity relation; 2) to consider properties from the non-monotonic reasoning literature and discuss their desirability, gaining more insight on the interactive explanation scenario.

Keywords

Cite

@article{arxiv.2208.00316,
  title  = {On Interactive Explanations as Non-Monotonic Reasoning},
  author = {Guilherme Paulino-Passos and Francesca Toni},
  journal= {arXiv preprint arXiv:2208.00316},
  year   = {2022}
}

Comments

Corrected version for the XAI-IJCAI 2022 workshop, expands on the XLoKR-KR 2022 workshop

R2 v1 2026-06-25T01:21:19.638Z