Skip to main content
. Author manuscript; available in PMC: 2024 Aug 28.
Published in final edited form as: Proc Mach Learn Res. 2024 Jul;235:53597–53618.

Figure 3.

Figure 3.

Consistency scores (higher is better) for DISCRET and a black-box model (TransTEE) combined with a post-hoc explainer. Our results confirm that DISCRET produces faithful explanations, and importantly, show that post-hoc explanations are rarely faithful, as evidenced by low consistency scores across datasets.