Interpretation of Black Box NLP Models: A Survey
This addresses the problem of unreliable model interpretations for users in high-stakes domains like finance and healthcare, but it is incremental as it builds on existing perturbation-based methods.
The paper tackles the instability of post-hoc explanation methods like LIME for interpreting black-box NLP models, proposing S-LIME to guarantee stability through hypothesis testing, with experiments showing effectiveness on simulated and real-world datasets.
An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare. Despite their superior performances, many models are black boxes in nature which are hard to explain. There are growing efforts for researchers to develop methods to interpret these black-box models. Post hoc explanations based on perturbations, such as LIME, are widely used approaches to interpret a machine learning model after it has been built. This class of methods has been shown to exhibit large instability, posing serious challenges to the effectiveness of the method itself and harming user trust. In this paper, we propose S-LIME, which utilizes a hypothesis testing framework based on central limit theorem for determining the number of perturbation points needed to guarantee stability of the resulting explanation. Experiments on both simulated and real world data sets are provided to demonstrate the effectiveness of our method.