back to list

Project: Credal models for reasoning shortcut awareness

Description

Reasoning shortcuts can be harmful for AI systems which want to achieve a high level of "understanding" and reasoning capabilities. The XOR MNIST example illustrates well the current situation (see https://arxiv.org/abs/2507.11357 and https://proceedings.mlr.press/v244/marconato24a.html). This project will attempt to use credal models to represent those situations and leverage their inference capabilities to resolve them. The work will study the paper in the first link and continue on how we can improve the shortcut awareness with a more powerful extended probabilistic representation. This is collaborative work with Dr Emile van Krieken (VU Amsterdam).

Details

Supervisor

Cassio de Campos

Interested?

Get in contact