CSE-472-Project-2: Understanding Text Classifiers with Counterfactual Explanation Mitigate Impact of Spurious Correlation for Text Classification with Counterfactual Methods Name Paper Code CLP [AAAI 2019] Counterfactual Fairness in Text Classification through Robustness PyTorch Corsair [ACL 2021] Counterfactual Inference for Text Classification Debiasing PyTorch AGC [AAAI 2021] Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals Pytorch Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations Name Paper Code DiCE [FAT 2021] Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations Tensorflow/PyTorch/sklearn Randomized sampling Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR DiCE Genetic algorithm A fast and elitist multiobjective genetic algorithm: NSGA-II DiCE KD-Tree Interpretable Counterfactual Explanations Guided by Prototypes DiCE An explicit loss-based method [FAT 2021] Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations Tensorflow/PyTorch VAE-based method Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers Tensorflow/PyTorch