An Analysis of LIME for Text Data

Dina Mardaoui · Damien Garreau

Keywords: [ Ethics and Safety ] [ Interpretable Statistics and Machine Learning ]

[ Abstract ]
Wed 14 Apr 6 a.m. PDT — 8 a.m. PDT
Oral presentation: Theory and Methods of Learning
Wed 14 Apr 8:15 a.m. PDT — 9:15 a.m. PDT


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.

Chat is not available.