Robustness

Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals ACL 2023 Window-Based Distribution Shift Detection for Deep Neural Networks NeurIPS 2023 A Nested Bi-level Optimization Framework for Robust Few Shot Learning AAAI 2022 An Investigation of the (In)effectiveness of Counterfactually Augmented Data ACL 2022 ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation CVPR 2022 ASSIST: Towards Label Noise-Robust Dialogue State Tracking ACL 2022 Autoregressive Perturbations for Data Poisoning NeurIPS 2022 Can Adversarial Training Be Manipulated By Non-Robust Features? NeurIPS 2022 Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models EMNLP 2022 CC-CERT: A Probabilistic Approach to Certify General Robustness of Neural Networks AAAI 2022 Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks AAAI 2022 Coresets for Wasserstein Distributionally Robust Optimization Problems NeurIPS 2022 Data-Driven Conditional Robust Optimization NeurIPS 2022 Debiasing NLU Models via Causal Intervention and Counterfactual Reasoning AAAI 2022 Deep Ensembles Work, But Are They Necessary? NeurIPS 2022 Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model ACL 2022 Does Robustness on ImageNet Transfer to Downstream Tasks? CVPR 2022 DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models EMNLP 2022 Enhancing Adversarial Training With Second-Order Statistics of Weights CVPR 2022 Evaluating Robustness to Dataset Shift via Parametric Robustness Sets NeurIPS 2022 Explicit Tradeoffs between Adversarial and Natural Distributional Robustness NeurIPS 2022 Exploring The Landscape of Distributional Robustness for Question Answering Models EMNLP 2022 Factored DRO: Factored Distributionally Robust Policies for Contextual Bandits NeurIPS 2022 Features or Spurious Artifacts? Data-centric Baselines for Fair and Robust Hate Speech Detection NAACL 2022 Finding Naturally Occurring Physical Backdoors in Image Datasets NeurIPS 2022