model robustness

Causal Augmentation for Causal Sentence Classification EMNLP 2021 DeepRobust: a Platform for Adversarial Attacks and Defenses AAAI 2021 Detoxifying Language Models Risks Marginalizing Minority Voices NAACL 2021 Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck NeurIPS 2021 Doing Good or Doing Right? Exploring the Weakness of Commonsense Causal Reasoning Models ACL 2021 DORO: Distributional and Outlier Robust Optimization ICML 2021 Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation ICCV 2021 Enhancing Model Robustness and Fairness with Causality: A Regularization Approach EMNLP 2021 Evaluating Deception Detection Model Robustness To Linguistic Variation NAACL 2021 Evaluating Model Robustness and Stability to Dataset Shift AISTATS 2021 Evaluating the Robustness of Neural Language Models to Input Perturbations EMNLP 2021 Explaining Deep Learning Models for Speech Enhancement Interspeech 2021 Exploring Targeted Universal Adversarial Perturbations to End-to-End ASR Models Interspeech 2021 Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis ACL 2021 Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption AAAI 2021 How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs? EMNLP 2021 How Emotionally Stable is ALBERT? Testing Robustness with Stochastic Weight Averaging on a Sentiment Analysis Task EMNLP 2021 Identifying and Benchmarking Natural Out-of-Context Prediction Problems NeurIPS 2021 Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries AAAI 2021 Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation EMNLP 2021 Improving Robustness of Facial Landmark Detection by Defending Against Adversarial Attacks ICCV 2021 Investigating Robustness of Dialog Models to Popular Figurative Language Constructs EMNLP 2021 Label-Only Membership Inference Attacks ICML 2021 Learnable Boundary Guided Adversarial Training ICCV 2021 Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection ACL 2021