Documenting evidence of a reuse of ‘“why should I trust you?”: explaining the predictions of any classifier’

By Kewen Peng, Tim Menzies. 2021

315 citations recorded by the source corpus.

We report here the following example of reuse. LIME is a local instance-based explanation generation framework that was originally proposed by Ribeiro et al. in their paper "'Why Should I Trust You?': Explaining the Predictions of Any Classifier". The framework was reused by Peng et al. in their paper "Defect Reduction Planning (using TimeLIME)". The paper used the original implementation of LIME as one of the core components in the proposed framework.

Subfields: Artificial Intelligence

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting (2019, neutral): “Post-hoc explanation methods, such as LIME [32], SHAP [27] and RL-LIM [40], are applied on pre-trained black-box models.”
Interpretable Neural Predictions with Differentiable Binary Variables (2019, positive): “Ribeiro et al. (2016) make any classiﬁer interpretable by approximating it locally with a linear proxy model in an approach called LIME, and Alvarez-Melis and Jaakkola (2017) propose a framework that returns input-output pairs that are causally related.”
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques (2019, unknown): “It also has LIME-like [47] methods for local post-hoc ex-plainability.”
Explaining models: an empirical study of how explanations impact fairness judgment (2019, unknown): “Much research is dedicated to generating explanations in various styles, including model-agnostic approaches [26, 30] applicable to any ML algorithm.”
Distilling Structured Knowledge into Embeddings for Explainable and Accurate Recommendation (2019, unknown): “LIME [30] proposed by Ribeiro et al.”
Combining Feature and Instance Attribution to Detect Artifacts (2021, methodology): “, tokens) in proportion to their “importance” for an output (Ribeiro et al., 2016; Lundberg and Lee, 2017; Adebayo et al., 2018), and; (2) instance attribution, where we retrieve training instances most responsible for a given prediction (Koh and Liang, 2017; Yeh et al.”
Machine Learning Testing: Survey, Landscapes and Horizons (2019, unknown): “10 Local Interpretable Model-agnostic Explanations produces decision trees corresponding to an input that could provide paths in symbolic execution [110]”