Explainable AI: learning from the learners

Résumé fourni par la source

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), used alongside causal reasoning and domain validation, enables learning from the learners. Focusing on discovery, optimization and certification, we show how foundation models and explainability methods can expose model-internal decision processes, generate candidate mechanistic hypotheses, guide robust design and control, and support trust and accountability in high-stakes applications. AI is increasingly solving more scientific and engineering problems, but its decisions are often hard to understand. Here, the authors argue that explainable AI, combined with causal reasoning and validation, can turn AI systems into partners for discovery, design and safer use.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.