Interpretability

SketchXAI: A First Look at Explainability for Human Sketches CVPR 2023 Symbolic Metamodels for Interpreting Black-Boxes Using Primitive Functions AAAI 2023 Testing the Channels of Convolutional Neural Networks AAAI 2023 The Analysis of Deep Neural Networks by Information Theory: From Explainability to Generalization AAAI 2023 The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources ACL 2023 Theoretical and Practical Perspectives on what Influence Functions Do NeurIPS 2023 Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions ACL 2023 Towards Robust Metrics for Concept Representation Evaluation AAAI 2023 Trade-off Between Efficiency and Consistency for Removal-based Explanations NeurIPS 2023 Trusted Fine-Grained Image Classification through Hierarchical Evidence Fusion AAAI 2023 Unsupervised Selective Rationalization with Noise Injection ACL 2023 Use perturbations when learning from explanations NeurIPS 2023 Variable-Based Calibration for Machine Learning Classifiers AAAI 2023 VeriX: Towards Verified Explainability of Deep Neural Networks NeurIPS 2023 Very Fast, Approximate Counterfactual Explanations for Decision Forests AAAI 2023 What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric ACL 2023 Why Did This Model Forecast This Future? Information-Theoretic Saliency for Counterfactual Explanations of Probabilistic Regression Models NeurIPS 2023 Acceptability Judgements via Examining the Topology of Attention Maps EMNLP 2022 A Comparative Study of Faithfulness Metrics for Model Interpretability Methods ACL 2022 Actionable Model-Centric Explanations (Student Abstract) AAAI 2022 Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology NeurIPS 2022 AI Explainability 360: Impact and Design AAAI 2022 Amortized Generation of Sequential Algorithmic Recourses for Black-Box Models AAAI 2022 Analyzing the Use of Influence Functions for Instance-Specific Data Filtering in Neural Machine Translation EMNLP 2022 An Unsupervised Way to Understand Artifact Generating Internal Units in Generative Neural Networks AAAI 2022