An Analysis of LIME for Text Data
This addresses the interpretability problem for users of text-based machine learning models, but it is incremental as it focuses on theoretical analysis for specific simple cases.
The paper tackled the lack of theoretical guarantees for LIME in explaining text data models, showing that LIME provides meaningful explanations for simple models like decision trees and linear models.
Text data are increasingly handled in an automated fashion by machine learning algorithms. But the models handling these data are not always well-understood due to their complexity and are more and more often referred to as "black-boxes." Interpretability methods aim to explain how these models operate. Among them, LIME has become one of the most popular in recent years. However, it comes without theoretical guarantees: even for simple models, we are not sure that LIME behaves accurately. In this paper, we provide a first theoretical analysis of LIME for text data. As a consequence of our theoretical findings, we show that LIME indeed provides meaningful explanations for simple models, namely decision trees and linear models.