Position: Explainable AI is Causality in Disguise
This addresses the fundamental discord in XAI for researchers and practitioners by advocating a shift towards causal methods, though it is a conceptual position rather than an incremental technical advance.
The paper argues that the fragmentation and unresolved challenges in Explainable AI (XAI) stem from a lack of causal grounding, proposing that causal models are necessary and sufficient for achieving explainability.
The demand for Explainable AI (XAI) has triggered an explosion of methods, producing a landscape so fragmented that we now rely on surveys of surveys. Yet, fundamental challenges persist: conflicting metrics, failed sanity checks, and unresolved debates over robustness and fairness. The only consensus on how to achieve explainability is a lack of one. This has led many to point to the absence of a ground truth for defining ``the'' correct explanation as the main culprit. This position paper posits that the persistent discord in XAI arises not from an absent ground truth but from a ground truth that exists, albeit as an elusive and challenging target: the causal model that governs the relevant system. By reframing XAI queries about data, models, or decisions as causal inquiries, we prove the necessity and sufficiency of causal models for XAI. We contend that without this causal grounding, XAI remains unmoored. Ultimately, we encourage the community to converge around advanced concept and causal discovery to escape this entrenched uncertainty.