Interpretability

AbductionRules: Training Transformers to Explain Unexpected Inputs ACL 2022 Abstract Rule Learning for Paraphrase Generation IJCAI 2022 Accelerating Shapley Explanation via Contributive Cooperator Selection ICML 2022 Acceptability Judgements via Examining the Topology of Attention Maps EMNLP 2022 Accurate Shapley Values for explaining tree-based models AISTATS 2022 A Closer Look at How Fine-tuning Changes BERT ACL 2022 A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection COLING 2022 A Comparative Study of Faithfulness Metrics for Model Interpretability Methods ACL 2022 A Computationally Grounded Logic of 'Seeing-to-it-that' IJCAI 2022 A Consistent and Efficient Evaluation Strategy for Attribution Methods ICML 2022 ACTA 2.0: A Modular Architecture for Multi-Layer Argumentative Analysis of Clinical Trials IJCAI 2022 Actionable Model-Centric Explanations (Student Abstract) AAAI 2022 Adaptive Conformal Predictions for Time Series ICML 2022 Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology NeurIPS 2022 Addressing Leakage in Concept Bottleneck Models NeurIPS 2022 Adversarial Concept Erasure in Kernel Space EMNLP 2022 Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs ACML 2022 Adversarially Robust Conformal Prediction ICLR 2022 Adversarially trained neural representations may already be as robust as corresponding biological neural representations ICML 2022 Adversarial Parametric Pose Prior CVPR 2022 Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation AAAI 2022 Adversarial Training on Disentangling Meaning and Language Representations for Unsupervised Quality Estimation COLING 2022 A Dynamical System Perspective for Lipschitz Neural Networks ICML 2022 AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis ICLR 2022 A Fine-grained Interpretability Evaluation Benchmark for Neural NLP CoNLL 2022