AI-framed questioning | G2: Make clear how well the system can do what it can do

blue header bar

Questions posed alongside GenAI outputs make clear how well the system can do what it can do (Guideline 2) by promoting critical thinking (Sarkar et al., 2024) and helping users correctly spot logical fallacies (Danry et al., 2023).

The techniques used in this example have the potential to foster appropriate reliance on AI, by reducing overreliance. Keep in mind that overreliance mitigations can backfire. Be sure to test such mitigations in context, with your AI system’s actual users. Learn more about overreliance on AI and appropriate reliance on generative AI.

The interface for displaying feedback to participants. Statement: Equality of opportunity is an ideal that cannot be realizes with governmental actions. The 2010 Equality Bill in Britain ended up being repealed. Feedback from the AI logical assessment system: If one bill in Britain did not lead to equality of opportunity, does it follow that equality of opportunity cannot be realized with other other government actions?
Image captured January 2025.