Interpretability

ATCON: Attention Consistency for Vision Models WACV 2023 A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations ICML 2023 Attention at SemEval-2023 Task 10: Explainable Detection of Online Sexism (EDOS) SemEval 2023 Attribution-based Explanations that Provide Recourse Cannot be Robust JMLR 2023 Augmentation by Counterfactual Explanation - Fixing an Overconfident Classifier WACV 2023 Augment to Interpret: Unsupervised and Inherently Interpretable Graph Embeddings ACML 2023 Augustine of Hippo at SemEval-2023 Task 4: An Explainable Knowledge Extraction Method to Identify Human Values in Arguments with SuperASKE SemEval 2023 A Unifying Framework to the Analysis of Interaction Methods using Synergy Functions ICML 2023 AU_NLP at SemEval-2023 Task 10: Explainable Detection of Online Sexism Using Fine-tuned RoBERTa SemEval 2023 Automatically Auditing Large Language Models via Discrete Optimization ICML 2023 Automatic speaker recognition with variation across vocal conditions: a controlled experiment with implications for forensics Interspeech 2023 Automating Behavioral Testing in Machine Translation EMNLP 2023 Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings NeurIPS 2023 Autonomous Justification for Enabling Explainable Decision Support in Human-Robot Teaming RSS 2023 AutoReply: Detecting Nonsense in Dialogue with Discriminative Replies EMNLP 2023 Backpack Language Models ACL 2023 Backtracking Counterfactuals CLeaR 2023 Bayesian Hierarchical Models for Counterfactual Estimation AISTATS 2023 Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts ICML 2023 Being Right for Whose Right Reasons? ACL 2023 BeliefPPG: Uncertainty-aware heart rate estimation from PPG signals via belief propagation UAI 2023 Benchmarking eXplainable AI - A Survey on Available Toolkits and Open Challenges IJCAI 2023 Beyond Black Box AI generated Plagiarism Detection: From Sentence to Document Level ACL 2023 Beyond calibration: estimating the grouping loss of modern neural networks ICLR 2023 Beyond Confidence: Reliable Models Should Also Consider Atypicality NeurIPS 2023