Dialogue Explanation With Reasoning for AI

Explainable Artificial Intelligence is increasingly gaining attention in domains, such as self-driving cars and medical treatment. One of the most prevalent issues with these explainable models is that they are difficult to comprehend and have not been tested in real-world scenarios. In this research, I propose a dialogue-based explanation with reasoning for a rule-based system with the intention of utilising it in the future with a Neuro Symbolic AI system, to give machines the capacity to explain their actions or decisions using logic. We hypothesize that when a system makes a deduction that was, in some way, unexpected by the user then locating the source of the disagreement or misunderstanding is best achieved through a collaborative dialogue process that allows the participants to gradually isolate the cause. I also conduct a user evaluation for this hypothesis.