CaBRNet, an open-source library for developing and evaluating Case-Based Reasoning Models
This work addresses reproducibility issues for researchers in explainable AI, though it is incremental as it builds on existing Case-Based Reasoning methods.
The authors tackled the lack of reproducibility and comparability in self-explainable AI models by developing CaBRNet, an open-source, modular framework for Case-Based Reasoning Networks, resulting in a publicly available tool at https://github.com/aiser-team/cabrnet.
In the field of explainable AI, a vibrant effort is dedicated to the design of self-explainable models, as a more principled alternative to post-hoc methods that attempt to explain the decisions after a model opaquely makes them. However, this productive line of research suffers from common downsides: lack of reproducibility, unfeasible comparison, diverging standards. In this paper, we propose CaBRNet, an open-source, modular, backward-compatible framework for Case-Based Reasoning Networks: https://github.com/aiser-team/cabrnet.