Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?

22 October 2021

Papers citing "Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?"

8 / 8 papers shown

Title
Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks? Thang M. Pham Trung Bui Long Mai Anh Totti Nguyen 224 124 0 30 Dec 2020
Feature Removal Is a Unifying Principle for Model Explanation Methods Ian Covert Scott M. Lundberg Su-In Lee FAtt 92 33 0 06 Nov 2020
Interpretation of NLP models through input marginalization Siwon Kim Jihun Yi Eunji Kim Sungroh Yoon MILM FAtt 39 58 0 27 Oct 2020
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance Gagan Bansal Tongshuang Wu Joyce Zhou Raymond Fok Besmira Nushi Ece Kamar Marco Tulio Ribeiro Daniel S. Weld 59 588 0 26 Jun 2020
e-SNLI: Natural Language Inference with Natural Language Explanations Oana-Maria Camburu Tim Rocktaschel Thomas Lukasiewicz Phil Blunsom LRM 367 634 0 04 Dec 2018
Real Time Image Saliency for Black Box Classifiers P. Dabkowski Y. Gal 38 586 0 22 May 2017
Learning Deep Features for Discriminative Localization Bolei Zhou A. Khosla Àgata Lapedriza A. Oliva Antonio Torralba SSL SSeg FAtt 131 9,266 0 14 Dec 2015
Visualizing and Understanding Convolutional Networks Matthew D. Zeiler Rob Fergus FAtt SSL 244 15,825 0 12 Nov 2013