All You Need for Counterfactual Explainability Is Principled and Reliable Estimate of Aleatoric and Epistemic Uncertainty
This is an incremental position paper for researchers in AI transparency and interpretability, suggesting a conceptual shift rather than new empirical results.
The paper argues that integrating uncertainty quantification into transparency research can address key challenges in counterfactual explainability, proposing that uncertainty provides a principled framework for generating human-centered explanations in inherently transparent models.
This position paper argues that, to its detriment, transparency research overlooks many foundational concepts of artificial intelligence. Here, we focus on uncertainty quantification -- in the context of ante-hoc interpretability and counterfactual explainability -- showing how its adoption could address key challenges in the field. First, we posit that uncertainty and ante-hoc interpretability offer complementary views of the same underlying idea; second, we assert that uncertainty provides a principled unifying framework for counterfactual explainability. Consequently, inherently transparent models can benefit from human-centred explanatory insights -- like counterfactuals -- which are otherwise missing. At a higher level, integrating artificial intelligence fundamentals into transparency research promises to yield more reliable, robust and understandable predictive models.