Interpretability

One Word, Two Sides: Traces of Stance in Contextualized Word Representations COLING 2022 On Neurons Invariant to Sentence Structural Changes in Neural Machine Translation CoNLL 2022 On Preferred Abductive Explanations for Decision Trees and Random Forests IJCAI 2022 On Quantifying Literals in Boolean Logic and its Applications to Explainable AI (Extended Abstract) IJCAI 2022 On the Complementarity of Images and Text for the Expression of Emotions in Social Media ACL 2022 On the Complexity of Enumerating Prime Implicants from Decision-DNNF Circuits IJCAI 2022 On the Diversity and Limits of Human Explanations NAACL 2022 On the Impact of Temporal Concept Drift on Model Explanations EMNLP 2022 On the Importance of Data Size in Probing Fine-tuned Models ACL 2022 On the Interpretability of Attention Networks ACML 2022 On the Nature of BERT: Correlating Fine-Tuning and Linguistic Competence COLING 2022 On the Pitfalls of Analyzing Individual Neurons in Language Models ICLR 2022 On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach NeurIPS 2022 On the Sensitivity and Stability of Model Interpretations in NLP ACL 2022 On the Symmetries of Deep Learning Models and their Internal Representations NeurIPS 2022 On the Transformation of Latent Space in Fine-Tuned NLP Models EMNLP 2022 Opening the Black Box: Automated Software Analysis for Algorithm Selection AutoML 2022 OpenXAI: Towards a Transparent Evaluation of Model Explanations NeurIPS 2022 Optimal Local Explainer Aggregation for Interpretable Prediction AAAI 2022 Optimizing Binary Decision Diagrams with MaxSAT for Classification AAAI 2022 Orientation Estimation of Abdominal Ultrasound Images with Multi-Hypotheses Networks MIDL 2022 OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks CVPR 2022 Outlier Dimensions that Disrupt Transformers are Driven by Frequency EMNLP 2022 Out of Distribution Detection via Neural Network Anchoring ACML 2022 Overconfidence in the Face of Ambiguity with Adversarial Data NAACL 2022