Interpretability

Augment to Interpret: Unsupervised and Inherently Interpretable Graph Embeddings ACML 2023 Auxiliary Losses for Learning Generalizable Concept-based Models NeurIPS 2023 Batchnorm Allows Unsupervised Radial Attacks NeurIPS 2023 Beyond Confidence: Reliable Models Should Also Consider Atypicality NeurIPS 2023 Black-box language model explanation by context length probing ACL 2023 Class based Influence Functions for Error Detection ACL 2023 COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP ACL 2023 Contrastive Learning with Adversarial Examples for Alleviating Pathology of Language Model ACL 2023 CREST: A Joint Framework for Rationalization and Counterfactual Text Generation ACL 2023 Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses NeurIPS 2023 Defining and Quantifying the Emergence of Sparse Concepts in DNNs CVPR 2023 DISCOVER: Making Vision Networks Interpretable via Competition and Dissection NeurIPS 2023 Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods ACL 2023 Efficient Shapley Values Estimation by Amortization for Text Classification ACL 2023 Emptying the Ocean with a Spoon: Should We Edit Models? EMNLP 2023 Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency NeurIPS 2023 Experimental Observations of the Topology of Convolutional Neural Network Activations AAAI 2023 Explainable Brain Age Prediction using coVariance Neural Networks NeurIPS 2023 Explaining How Transformers Use Context to Build Predictions ACL 2023 Explaining Random Forests Using Bipolar Argumentation and Markov Networks AAAI 2023 GaitGCI: Generative Counterfactual Intervention for Gait Recognition CVPR 2023 Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis AAAI 2023 IAEval: A Comprehensive Evaluation of Instance Attribution on Natural Language Understanding EMNLP 2023 Incorporating Attribution Importance for Improving Faithfulness Metrics ACL 2023 Initialization Noise in Image Gradients and Saliency Maps CVPR 2023