Interpretability

Rethinking Influence Functions of Neural Networks in the Over-Parameterized Regime AAAI 2022 Rethinking the Authorship Verification Experimental Setups EMNLP 2022 Reverse Differentiation via Predictive Coding AAAI 2022 REX: Reasoning-Aware and Grounded Explanation CVPR 2022 Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence EMNLP 2022 Right for the Right Reason: Evidence Extraction for Trustworthy Tabular Reasoning ACL 2022 Risk-graded Safety for Handling Medical Queries in Conversational AI AACL 2022 RKHS-SHAP: Shapley Values for Kernel Methods NeurIPS 2022 RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees EMNLP 2022 Robust Bayesian recourse UAI 2022 Robust Feature-Level Adversaries are Interpretability Tools NeurIPS 2022 Robust Graph Neural Networks via Probabilistic Lipschitz Constraints L4DC 2022 Robust Interpretable Text Classification against Spurious Correlations Using AND-rules with Negation IJCAI 2022 RobustLR: A Diagnostic Benchmark for Evaluating Logical Robustness of Deductive Reasoners EMNLP 2022 Robust Models Are More Interpretable Because Attributions Look Normal ICML 2022 Robustness Certificates for Implicit Neural Networks: A Mixed Monotone Contractive Approach L4DC 2022 Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions EMNLP 2022 RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators NAACL 2022 RuCoLA: Russian Corpus of Linguistic Acceptability EMNLP 2022 Safe Neurosymbolic Learning with Differentiable Symbolic Execution ICLR 2022 Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer CoRL 2022 SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction NAACL 2022 Salient ImageNet: How to discover spurious features in Deep Learning? ICLR 2022 SALTED: A Framework for SAlient Long-tail Translation Error Detection EMNLP 2022 Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models NAACL 2022