Faithful and Robust Local Interpretability for Textual Predictions

arXiv:2311.01605v2 Announce Type: replace-cross
Abstract: Interpretability is essential for machine learning models to be trusted and deployed in critical domains. However, existing methods for interpreting text models are often complex, lack mathematical foundations, and their performance is not guaranteed. In this paper, we propose FRED (Faithful and Robust Explainer for textual Documents), a novel method for interpreting predictions over text. FRED offers three key insights to explain a model prediction: (1) it identifies the minimal set of words in a …

abstract arxiv cs.cl cs.lg documents domains explainer however interpretability machine machine learning machine learning models paper performance predictions robust stat.ml text textual type