Can counterfactual explanations of AI systems' predictions skew lay users' causal intuitions about the world? If so, can we correct for that?

1 code implementation • 12 May 2022 • Marko Tesic, Ulrike Hahn

We found that pointing out that AI systems capture correlations and not necessarily causal relationships can attenuate the effects of CF explanations on people's causal beliefs.

counterfactual Misinformation