Interpretability

G–LIME: Statistical Learning for Local Interpretations of Deep Neural Networks Using Global Priors (Abstract Reprint) AAAI 2024 Identifying Important Group of Pixels using Interactions CVPR 2024 Improving Explainable Fact-Checking via Sentence-Level Factual Reasoning EMNLP 2024 Information Flow Routes: Automatically Interpreting Language Models at Scale EMNLP 2024 InternalInspector I2: Robust Confidence Estimation in LLMs through Internal States EMNLP 2024 InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques NeurIPS 2024 Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE) NeurIPS 2024 Interpreting Learned Feedback Patterns in Large Language Models NeurIPS 2024 Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning AAAI 2024 Path Choice Matters for Clear Attributions in Path Methods ICLR 2024 PICNN: A Pathway towards Interpretable Convolutional Neural Networks AAAI 2024 Q-SENN: Quantized Self-Explaining Neural Networks AAAI 2024 Representational Analysis of Binding in Language Models EMNLP 2024 Transformer Doctor: Diagnosing and Treating Vision Transformers NeurIPS 2024 Validation, Robustness, and Accuracy of Perturbation-Based Sensitivity Analysis Methods for Time-Series Deep Learning Models AAAI 2024 Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models CVPR 2024 Adversarial Normalization: I Can Visualize Everything (ICE) CVPR 2023 Better Loss Landscape Visualization for Deep Neural Networks with Trajectory Information ACML 2023 Does Deep Learning Learn to Abstract? A Systematic Probing Framework ICLR 2023 Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency NeurIPS 2023 Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis AAAI 2023 Improving Interpretability via Explicit Word Interaction Graph Layer AAAI 2023 Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small ICLR 2023 Interpretability with full complexity by constraining feature information ICLR 2023 Log-linear Guardedness and its Implications ACL 2023