Interpretability

Composition, Attention, or Both? EMNLP 2022 Concept Activation Regions: A Generalized Framework For Concept-Based Explanations NeurIPS 2022 Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off NeurIPS 2022 Concept Learning for Interpretable Multi-Agent Reinforcement Learning CoRL 2022 CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning NAACL 2022 Conformal Prediction with Temporal Quantile Adjustments NeurIPS 2022 Consistent Counterfactuals for Deep Models ICLR 2022 Consistent Explanations by Contrastive Learning CVPR 2022 Consistent Sufficient Explanations and Minimal Local Rules for explaining the decision of any classifier or regressor NeurIPS 2022 Constrained Predictive Coding as a Biologically Plausible Model of the Cortical Hierarchy NeurIPS 2022 Constraint-Driven Explanations for Black-Box ML Models AAAI 2022 Consultation Checklists: Standardising the Human Evaluation of Medical Note Generation EMNLP 2022 Contrastive Explanations of Text Classifiers as a Service NAACL 2022 Controlling Bias Exposure for Fair Interpretable Predictions EMNLP 2022 Controlling the Focus of Pretrained Language Generation Models ACL 2022 Convergent Representations of Computer Programs in Human and Artificial Neural Networks NeurIPS 2022 Counterfactual Explanations for Natural Language Interfaces ACL 2022 Counterfactual Explanation Trees: Transparent and Consistent Actionable Recourse with Decision Trees AISTATS 2022 Counterfactual inference of second Opinions UAI 2022 Counterfactual Interpolation Augmentation (CIA): A Unified Approach to Enhance Fairness and Explainability of DNN IJCAI 2022 Counterfactual Plans under Distributional Ambiguity ICLR 2022 CounteRGAN: Generating counterfactuals for real-time recourse and interpretability using residual GANs UAI 2022 Covered Information Disentanglement: Model Transparency via Unbiased Permutation Importance AAAI 2022 Creating Interpretable Data-Driven Approaches for Tropical Cyclones Forecasting AAAI 2022 Creativity of AI: Automatic Symbolic Option Discovery for Facilitating Deep Reinforcement Learning AAAI 2022