Experiment and brainstorm different explainable interfaces.
Imagine you are creating an AI helper that can assist people in determining whether or not a plant is safe or poisonous. The AI helper is imperfect, therefore how might we help people determine whether to trust its prediction or use their own judgment?
In this particular instance, a person finds a blue, spotted, thorny, large plant. The AI thinks it's poisonous, but should the person trust its prediction?
Where do I get started?
Explore how different question and explanation types can apply to this scenario by browsing and selecting a card below. Note that some explanation types may be better suited for this scenario based on the user, their goals, and the underlying model.
You can also download these cards to explore how they may be applied to your work and/or to other scenarios.
Why did the system do ____?
Why did the system decide this plant is poisonous?
Why did the system not do ___?
Why did the system not decide this plant is safe?
What would the system do if ___ happens?
What would the system predict if the plant was smooth instead of thorny?
How (under what condition) does it do ___?
How does the system decide a plant is poisonous?
What are the changes required for this instance to get a different prediction?
What would need to change for this plant to be predicted safe?
Still Be This
What is the scope of change permitted to still get the same prediction?
How much would need to change for this plant to still be predicted poisonous?
How certain is the system in a prediction or outcome?
How certain is the system that this plant is poisonous?
What data does the system learn from?
What information does the system use to determine whether a plant is safe or poisonous?
What are the possible outputs that the system can produce?
What can the system detect about this plant?
How It Works
What is the overall model of how the system works?
How does the system make its predictions?
Decision Tree Approximation
Feature Importance and Saliency
Rules or Trees
Contrastive or Counterfactual Features
Prototypical or Representative Examples
Feature Influence or Relevance
- Google. (n.d.). People AI Guidebook.
- Liao, Q. V., Gruen, D., & Miller, S. (2020). Questioning the AI: Informing Design Practices for Explainable AI User Experiences. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems - CHI 20.
- Lim, B.Y., & Dey, A.K. (2009). Assessing demand for intelligibility in context-aware applications. Proceedings of the 11th international conference on Ubiquitous computing.
- Lim, B.Y., Dey, A.K., & Avrahami, D. (2009). Why and why not explanations improve the intelligibility of context-aware intelligent systems. CHI.
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License