Interpretability

Training Private Models That Know What They Don’t Know NeurIPS 2023 Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks NeurIPS 2023 TRAK: Attributing Model Behavior at Scale ICML 2023 Transformer Meets Boundary Value Inverse Problems ICLR 2023 Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars NeurIPS 2023 Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships NeurIPS 2023 Transparency at the Source: Evaluating and Interpreting Language Models With Access to the True Distribution EMNLP 2023 Tree-Structured Shading Decomposition ICCV 2023 Trigger-Argument based Explanation for Event Detection ACL 2023 Two-stage holistic and contrastive explanation of image classification UAI 2023 Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization NeurIPS 2023 Uncertainty Quantification via Neural Posterior Principal Components NeurIPS 2023 Uncovering the Root of Hate Speech: A Dataset for Identifying Hate Instigating Speech EMNLP 2023 Understanding and Enhancing Robustness of Concept-Based Models AAAI 2023 Understanding Deep Generative Models With Generalized Empirical Likelihoods CVPR 2023 Understanding Influence Functions and Datamodels via Harmonic Analysis ICLR 2023 Understanding Programs by Exploiting (Fuzzing) Test Cases ACL 2023 Understanding Social Reasoning in Language Models with Language Models NeurIPS 2023 Understanding the Inner-workings of Language Models Through Representation Dissimilarity EMNLP 2023 Understanding Transformer Memorization Recall Through Idioms EACL 2023 Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data ICML 2023 Unfooling Perturbation-Based Post Hoc Explainers AAAI 2023 Unifying local and global model explanations by functional decomposition of low dimensional structures AISTATS 2023 Unisa at SemEval-2023 Task 3: A SHAP-based method for Propaganda Detection SemEval 2023 Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization NeurIPS 2023