Association for Computational Linguistics " Why Should I Trust You? " Explaining the Predictions of Any Classifier

By Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin. 2016

Subfields: Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation (2020, methodology): “We use the LIME toolkit (Ribeiro et al., 2016) to understand how the fine-tuning recipe yields such a strong model of pronoun gender.”
SELFEXPLAIN: A Self-Explaining Architecture for Neural Text Classifiers (2021, methodology): “While post-hoc methods (Simonyan et al., 2014; Koh and Liang, 2017; Ribeiro et al., 2016) are often the only option 1 Code and data is publicly available at https:// github.com/dheerajrajagopal/SelfExplain”
Benefits of Intermediate Annotations in Reading Comprehension (2020, background): “, 2017), which, similar to our annotations, identify parts of the input that are important for prediction (Lei et al., 2016; Ribeiro et al., 2016).”
e-SNLI: Natural Language Inference with Natural Language Explanations (2018, methodology): “[24] present a document classifier that distinguishes between Christianity and Atheism with an accuracy of 94%.”
Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models (2021, background): “, LIME (Ribeiro et al., 2016) and SHAP (Lundberg and Lee, 2017)).”
Axiomatic Attribution for Deep Networks (2017, background): “One approach to the attribution problem proposed ﬁrst by (Ribeiro et al., 2016a;b), is to locally approximate the behavior of the network in the vicinity of the input being explained with a simpler, more interpretable model.”
Social Bias Frames: Reasoning about Social and Power Implications of Language (2019, background): “In addition, detailed explanations are much more informative for people to understand and reason about why a statement is potentially harmful against other people (Gregor and Benbasat, 1999; Ribeiro et al., 2016).”
Visual Entailment: A Novel Task for Fine-Grained Image Understanding (2019, background): “Recent work addresses this requirement either through saliency-map visualizations [61, 77, 49], attention mechanism [75, 79, 51, 14], or other analysis [30, 39, 56, 58].”
Semantically Equivalent Adversarial Rules for Debugging NLP models (2018, background): “Previous work on debugging primarily focuses on explaining predictions in validation data in order to uncover bugs (Ribeiro et al., 2016, 2018; Kulesza et al., 2011), or find labeling errors (Zhang et al., 2018; Koh and Liang, 2017).”
Understanding Black-box Predictions via Influence Functions (2017, background): “Copyright 2017 by the author(s). point (Ribeiro et al., 2016) or by perturbing the test point to see how the prediction changes (Simonyan et al., 2013; Li et al., 2016b; Datta et al., 2016; Adler et al., 2016).”
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, positive): “Following the taxonomy introduced in Section 2 , model-agnostic techniques may rely on model simpliﬁcation, feature relevance estimation and visualization techniques: [32] and all its variations [214,216] .”
Explaining Explanations: An Overview of Interpretability of Machine Learning (2018, methodology): “1) Linear Proxy Models: The proxy model approach is exempliﬁed well by the LIME method by Ribeiro [20].”