ADIX is a project funded by ERC under the Advanced scheme (2021-2026). ADIX strives towards a radical re-thinking of explainable AI that can work in synergy with humans within a human-centred but AI-supported society. It aims to define a novel scientific paradigm of deep, interactive explanations that can be deployed alongside a variety of data-centric AI methods to explain their outputs by providing justifications in their support. These can be progressively questioned by humans and the outputs of the AI methods refined as a result of human feedback, within explanatory exchanges between humans and machines. This paradigm is being realised using computational argumentation as the underpinning, unifying theoretical foundation. The project aims to
- Define argumentative abstractions of the inner workings of a variety of data-centric AI methods from which various explanation types, providing argumentative grounds for outputs, can be drawn;
- Generate explanatory exchanges between humans and machines from interaction patterns instantiated on the argumentative abstractions and explanation types;
- Develop argumentative wrappers from human feedback.
The ADIX paradigm is being informed and tested by experiments and empirical evaluations in healthcare and law.
Funding
See the description of the project on the funder's website.
