Next generation artificial intelligence: explainable AI

UKRI and EPSRC are funding speculative, high-risk fundamental research with the potential to produce a step change in the explainability of future AI systems. The call welcomes work on mechanistic interpretability, output reasoning, process examination, imposed explainability, uncertainty quantification, and novel approaches beyond those examples.

Applicants must meet standard UKRI eligibility requirements and be based at an eligible UK research organisation. Early- and mid-career researchers are particularly encouraged; eligible international researchers may participate through the specified cooperation agreements or as collaborators.