Explainable AI: Learning from the Learners
This work addresses the need for transparency and accountability in AI for science and engineering, though it is incremental as it builds on existing XAI and causal reasoning concepts.
The paper tackles the problem of opaque AI representations by proposing explainable AI (XAI) combined with causal reasoning to enable learning from AI systems, focusing on discovery, optimization, and certification to extract causal mechanisms and support trust in high-stakes applications.
Artificial intelligence now outperforms humans in several scientific and engineering tasks, yet its internal representations often remain opaque. In this Perspective, we argue that explainable artificial intelligence (XAI), combined with causal reasoning, enables {\it learning from the learners}. Focusing on discovery, optimization and certification, we show how the combination of foundation models and explainability methods allows the extraction of causal mechanisms, guides robust design and control, and supports trust and accountability in high-stakes applications. We discuss challenges in faithfulness, generalization and usability of explanations, and propose XAI as a unifying framework for human-AI collaboration in science and engineering.