Interpretability

Explaining Preferences with Shapley Values NeurIPS 2022 Explaining Toxic Text via Knowledge Enhanced Text Generation NAACL 2022 Explaining Translationese: why are Neural Classifiers Better and what do they Learn? EMNLP 2022 ExplainIt!: A Tool for Computing Robust Attributions of DNNs IJCAI 2022 Explanations of Black-Box Models based on Directional Feature Interactions ICLR 2022 Explicit Alignment Learning for Neural Machine Translation IJCAI 2022 Exploiting Explainable Metrics for Augmented SGD CVPR 2022 Exploiting Numerical-Contextual Knowledge to Improve Numerical Reasoning in Question Answering NAACL 2022 Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection NeurIPS 2022 Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity EMNLP 2022 Exploring the Effects of Negation and Grammatical Tense on Bias Probes AACL 2022 Exploring the Latent Space of Autoencoders with Interventional Assays NeurIPS 2022 Exploring the Universal Vulnerability of Prompt-based Learning Paradigm NAACL 2022 Exposure Normalization and Compensation for Multiple-Exposure Correction CVPR 2022 ExSum: From Local Explanations to Model Understanding NAACL 2022 Extending Decision Tree to Handle Multiple Fairness Criteria IJCAI 2022 Extending Logic Explained Networks to Text Classification EMNLP 2022 Extracting computational mechanisms from neural data using low-rank RNNs NeurIPS 2022 Extracting Operator Trees from Model Embeddings EMNLP 2022 Fair and Optimal Decision Trees: A Dynamic Programming Approach NeurIPS 2022 Fair Conformal Predictors for Applications in Medical Imaging AAAI 2022 FaiRR: Faithful and Robust Deductive Reasoning over Natural Language ACL 2022 Faithful to the Document or to the World? Mitigating Hallucinations via Entity-Linked Knowledge in Abstractive Summarization EMNLP 2022 Fast Generic Interaction Detection for Model Interpretability and Compression ICLR 2022 Fast predictive uncertainty for classification with Bayesian deep networks UAI 2022