In human explanations we expect coherence over time, that is the explanations given at one point will be consistent with future behaviour and explanations unless something has changed. This suggests that explainable AI should behave in a similar fashion.
Links:
doi.org: Interactive explainability: Black boxes, mutual understanding and what it would really mean for AI systems to be as explainable as people. Myers and Chater, (2024)- alandix.com: Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction. Dix, Turchi, Wilson, Monreale and Roach. (2025).