Explanatory Decoupling
A phenomenon where a robustness intervention removes a model's reliance on a spurious cue without altering what the model attends to, indicating attribution stability does not guarantee semantic grounding.
Source: X-FCA: Diagnosing Explanatory Decoupling in Financial Information Systems via Counterfactual XAI and Conformal Prediction (Academic research) · p.2
Have a question about Explanatory Decoupling? Ask the AI, answers cite the source.