Gustau Camps-Valls: A Critical Look at Explainable AI

I will give a sarcastic and quite op-ed tour trying to explain why XAI is misleading us. Everything from SHAP plots to counterfactuals may look trustworthy, but underneath, they're often driven by correlations, not causation.

In fields like climate, neuroscience and social sciences, that's a serious risk. Inspired by philosophy of science, I argue that explanations must go beyond surface patterns. Fortunately, the frontier is moving fast: causal‐informed SHAP, meaningful counterfactuals (you can't go younger), causal certification in explanations, and structural causal modeling are all promising. 

Yet, it's time we treat XAI not just as a cosmetic fix, but as a tool grounded in truth: seamful, thought-provoking, and scientifically defensible. And if time allows I'd like to say a few words about why AI needs a new philosophy of science.

Gustau Camps-Valls is a Full Professor of Electrical Engineering at the Universitat de València, where he leads the Image and Signal Processing (ISP) group. His research lives at the intersection of machine learning and Earth system science, focusing on combining deep learning with physical laws to better model and understand climate change. A widely recognized global leader in his field, he is Program Director of the ELLIS Machine Learning for Earth and Climate Sciences program. 

He is a Fellow of the IEEE, ACM, AGU, and Academia Europaea, and a highly cited researcher. His work has been supported by prestigious European Research Council (ERC) Consolidator and Synergy grants, and he was recently awarded the 2025 Blaise Pascal Medal. Beyond his research, he serves as a convener for the United Nations’ ITU AI for Good seminar series and holds visiting positions at the Institut Polytechnique de Paris and the Max Planck Institute. https://isp.uv.es