Hana Chockler, "Using causality for debugging and explainability", VeTSS Annual Conference 2026

Talk by Hana Chockler (King’s College London), at the VeTSS Annual Conference, 12th May 2026, Royal Academy of Engineering, London, UK. Using causality for debugging and explainability In this talk I will look at the applications of actual causality to debugging models and explainability. Specifically, I will talk about actual causality as introduced by Halpern and Pearl, and its quantitative extensions. This theory turns out to be extremely useful in various areas of computer science due to a good match between the results it produces and our intuition. It turns out to be particularly useful for explaining the outputs of large AI systems. I will argue that explainability can be viewed as a debugging technique and illustrate this approach with a number of examples. I will discuss the differences between the traditional view of explainability as a human-oriented technique and the type of explainability we are proposing, which is essentially a window inside the (otherwise black-box) system.