Towards A Rigorous Science of Interpretable Machine Learning
This work addresses the need for standardized evaluation in interpretable machine learning, which is crucial for ensuring safety and fairness in AI systems, but it is incremental as it builds on existing discussions without introducing new methods.
The paper tackles the lack of consensus in interpretable machine learning by defining interpretability and proposing a taxonomy for rigorous evaluation, aiming to establish a more scientific foundation for the field.
As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such as safety or non-discrimination. However, despite the interest in interpretability, there is very little consensus on what interpretable machine learning is and how it should be measured. In this position paper, we first define interpretability and describe when interpretability is needed (and when it is not). Next, we suggest a taxonomy for rigorous evaluation and expose open questions towards a more rigorous science of interpretable machine learning.