Interpretability

MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes CVPR 2024 Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models NeurIPS 2024 MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment AAAI 2024 Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory NeurIPS 2024 Monotonic Representation of Numeric Attributes in Language Models ACL 2024 Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics NeurIPS 2024 On the Concept Trustworthiness in Concept Bottleneck Models AAAI 2024 On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods AAAI 2024 On the Universal Truthfulness Hyperplane Inside LLMs EMNLP 2024 RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks NeurIPS 2024 Relational Concept Bottleneck Models NeurIPS 2024 Robust Stochastic Graph Generator for Counterfactual Explanations AAAI 2024 Selective Explanations NeurIPS 2024 SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology CVPR 2024 SLICE: Stabilized LIME for Consistent Explanations for Image Classification CVPR 2024 Stochastic Concept Bottleneck Models NeurIPS 2024 The Intelligible and Effective Graph Neural Additive Network NeurIPS 2024 The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis EMNLP 2024 Too Big to Fail: Larger Language Models are Disproportionately Resilient to Induction of Dementia-Related Linguistic Anomalies ACL 2024 Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation CVPR 2024 Training Data Attribution via Approximate Unrolling NeurIPS 2024 Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models CVPR 2024 What Does Parameter-free Probing Really Uncover? ACL 2024 Accountability Layers: Explaining Complex System Failures by Parts AAAI 2023 Assessing Word Importance Using Models Trained for Semantic Tasks ACL 2023