model interpretability

Domino: Discovering Systematic Errors with Cross-Modal Embeddings ICLR 2022 Double Trouble: How to not Explain a Text Classifier’s Decisions Using Counterfactuals Synthesized by Masked Language Models? AACL 2022 Efficient Model-Driven Network for Shadow Removal AAAI 2022 ER-Test: Evaluating Explanation Regularization Methods for Language Models EMNLP 2022 Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining EMNLP 2022 Explaining Classes through Stable Word Attributions ACL 2022 Explaining Preferences with Shapley Values NeurIPS 2022 ExSum: From Local Explanations to Model Understanding NAACL 2022 Fair and Optimal Decision Trees: A Dynamic Programming Approach NeurIPS 2022 Fast Generic Interaction Detection for Model Interpretability and Compression ICLR 2022 Flexible Instance-Specific Rationalization of NLP Models AAAI 2022 FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles AAAI 2022 FR: Folded Rationalization with a Unified Encoder NeurIPS 2022 Interpretable Low-Resource Legal Decision Making AAAI 2022 Interpreting Language Models with Contrastive Explanations EMNLP 2022 Interpreting Time-Varying Dynamic Bayesian Networks for Earth Climate Modelling PGM 2022 Investigating the Benefits of Free-Form Rationales EMNLP 2022 KerGNNs: Interpretable Graph Neural Networks with Graph Kernels AAAI 2022 Lazy Estimation of Variable Importance for Large Neural Networks ICML 2022 Let the CAT out of the bag: Contrastive Attributed explanations for Text EMNLP 2022 Linear tree shap NeurIPS 2022 LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models EMNLP 2022 Locally Aggregated Feature Attribution on Natural Language Model Understanding NAACL 2022 Locally Distributed Activation Vectors for Guided Feature Attribution COLING 2022 Logic Traps in Evaluating Attribution Scores ACL 2022