feature attribution

Don’t be fooled: label leakage in explanation methods and the importance of their quantitative evaluation AISTATS 2023 Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods EMNLP 2023 Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods ACL 2023 Efficient Shapley Values Estimation by Amortization for Text Classification ACL 2023 Explaining Predictive Uncertainty with Information Theoretic Shapley Values NeurIPS 2023 Faith-Shap: The Faithful Shapley Interaction Index JMLR 2023 FEAMOE: Fair, Explainable and Adaptive Mixture of Experts IJCAI 2023 Feature Interactions Reveal Linguistic Structure in Language Models ACL 2023 Fooling SHAP with Stealthily Biased Sampling ICLR 2023 HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation ICML 2023 Incorporating Attribution Importance for Improving Faithfulness Metrics ACL 2023 Initialization Noise in Image Gradients and Saliency Maps CVPR 2023 Inseq: An Interpretability Toolkit for Sequence Generation Models ACL 2023 InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations EMNLP 2023 Interventional SHAP Values and Interaction Values for Piecewise Linear Regression Trees AAAI 2023 Investigating the Saliency of Sentiment Expressions in Aspect-Based Sentiment Analysis ACL 2023 Learning Perturbations to Explain Time Series Predictions ICML 2023 Learning to Estimate Shapley Values with Vision Transformers ICLR 2023 Local Explanations for Reinforcement Learning AAAI 2023 Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning NeurIPS 2023 Local Path Integration for Attribution AAAI 2023 Manifold Restricted Interventional Shapley Values AISTATS 2023 MGR: Multi-generator Based Rationalization ACL 2023 MultiViz: Towards Visualizing and Understanding Multimodal Models ICLR 2023 Negative Flux Aggregation to Estimate Feature Attributions IJCAI 2023