Interpretability

Locally Sparse Neural Networks for Tabular Biomedical Data ICML 2022 Local Structure Matters Most in Most Languages AACL 2022 Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models EMNLP 2022 LOGICDEF: An Interpretable Defense Framework against Adversarial Examples via Inductive Scene Graph Reasoning AAAI 2022 Logic Rule Guided Attribution with Dynamic Ablation AAAI 2022 Logic Rules Meet Deep Learning: A Novel Approach for Ship Type Classification (Extended Abstract) IJCAI 2022 LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning EMNLP 2022 Logic Traps in Evaluating Attribution Scores ACL 2022 Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning NeurIPS 2022 LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification AAAI 2022 LSCDiscovery: A shared task on semantic change discovery and detection in Spanish ACL 2022 Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations EMNLP 2022 Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure NeurIPS 2022 Manipulating SHAP via Adversarial Data Perturbations (Student Abstract) AAAI 2022 MBTI Personality Prediction for Fictional Characters Using Movie Scripts EMNLP 2022 Meaningfully debugging model mistakes using conceptual counterfactual explanations ICML 2022 Measuring Alignment Bias in Neural Seq2seq Semantic Parsers NAACL 2022 Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignment NAACL 2022 Measuring Context-Word Biases in Lexical Semantic Datasets EMNLP 2022 Measuring Morphological Fusion Using Partial Information Decomposition COLING 2022 Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing ICLR 2022 Measuring the Mixing of Contextual Information in the Transformer EMNLP 2022 Measuring the robustness of Gaussian processes to kernel choice AISTATS 2022 MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure EMNLP 2022 METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation NAACL 2022