Interpretability

Dr ChatGPT tell me what I want to hear: How different prompts impact health answer correctness EMNLP 2023 DRGCoder: Explainable Clinical Coding for the Early Prediction of Diagnostic-Related Groups EMNLP 2023 Drift doesn't Matter: Dynamic Decomposition with Diffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection NeurIPS 2023 Drop Clause: Enhancing Performance, Robustness and Pattern Recognition Capabilities of the Tsetlin Machine AAAI 2023 D-Separation for Causal Self-Explanation NeurIPS 2023 Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers NeurIPS 2023 Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods EMNLP 2023 Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods ACL 2023 Editing Common Sense in Transformers EMNLP 2023 Effective Human-AI Teams via Learned Natural Language Rules and Onboarding NeurIPS 2023 Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encoding (Extended Abstract) IJCAI 2023 Efficient SAGE Estimation via Causal Structure Learning AISTATS 2023 Efficient Shapley Values Estimation by Amortization for Text Classification ACL 2023 Efficient Symbolic Policy Learning with Differentiable Symbolic Expression NeurIPS 2023 eForecaster: Unifying Electricity Forecasting with Robust, Flexible, and Explainable Machine Learning Algorithms AAAI 2023 Eliminating the Impossible, Whatever Remains Must Be True: On Extracting and Applying Background Knowledge in the Context of Formal Explanations AAAI 2023 Emergent Linear Representations in World Models of Self-Supervised Sequence Models EMNLP 2023 Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task ICLR 2023 Emptying the Ocean with a Spoon: Should We Edit Models? EMNLP 2023 Enabling Knowledge Refinement upon New Concepts in Abductive Learning AAAI 2023 Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency NeurIPS 2023 E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition ACL 2023 Energy-based Out-of-Distribution Detection for Graph Neural Networks ICLR 2023 Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information EMNLP 2023 Enhancing Datalog Reasoning with Hypertree Decompositions IJCAI 2023