Interpretability

Measuring Context-Word Biases in Lexical Semantic Datasets EMNLP 2022 Model Distillation for Faithful Explanations of Medical Code Predictions ACL 2022 Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers AAAI 2022 Neural Basis Models for Interpretability NeurIPS 2022 No Free Lunch from Deep Learning in Neuroscience: A Case Study through Models of the Entorhinal-Hippocampal Circuit NeurIPS 2022 On the data requirements of probing ACL 2022 On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity NeurIPS 2022 On the Sensitivity and Stability of Model Interpretations in NLP ACL 2022 On the Symmetries of Deep Learning Models and their Internal Representations NeurIPS 2022 Optimal Local Explainer Aggregation for Interpretable Prediction AAAI 2022 Optimizing Binary Decision Diagrams with MaxSAT for Classification AAAI 2022 Pre-activation Distributions Expose Backdoor Neurons NeurIPS 2022 Probing for Constituency Structure in Neural Language Models EMNLP 2022 ProtGNN: Towards Self-Explaining Graph Neural Networks AAAI 2022 RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection NeurIPS 2022 RES: An Interpretable Replicability Estimation System for Research Publications AAAI 2022 Rethinking Influence Functions of Neural Networks in the Over-Parameterized Regime AAAI 2022 Right for the Right Reason: Evidence Extraction for Trustworthy Tabular Reasoning ACL 2022 RKHS-SHAP: Shapley Values for Kernel Methods NeurIPS 2022 Scalable Interpretability via Polynomials NeurIPS 2022 Scaling Up Influence Functions AAAI 2022 SkinCon: A skin disease dataset densely annotated by domain experts for fine-grained debugging and analysis NeurIPS 2022 Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection NeurIPS 2022 Sufficient Reasons for Classifier Decisions in the Presence of Domain Constraints AAAI 2022 Supervising Model Attention with Human Explanations for Robust Natural Language Inference AAAI 2022