One Explanation Does Not Fit XIL
This work addresses the need for more robust model debugging in AI systems, though it appears incremental as it builds on the existing XIL framework by exploring multiple explanations.
The paper tackles the problem of shortcut learning and spurious correlations in machine learning models by investigating the use of multiple explanation methods within the explanatory interactive machine learning (XIL) framework, finding that a single explanation is insufficient for effective model revision.
Current machine learning models produce outstanding results in many areas but, at the same time, suffer from shortcut learning and spurious correlations. To address such flaws, the explanatory interactive machine learning (XIL) framework has been proposed to revise a model by employing user feedback on a model's explanation. This work sheds light on the explanations used within this framework. In particular, we investigate simultaneous model revision through multiple explanation methods. To this end, we identified that \textit{one explanation does not fit XIL} and propose considering multiple ones when revising models via XIL.