Interpretability

Tracing and Manipulating intermediate values in Neural Math Problem Solvers EMNLP 2022 Tracking Down Misguiding Terms for Locating Bugs in Deep Learning-Based Software (Student Abstract) AAAI 2022 Tractable Function-Space Variational Inference in Bayesian Neural Networks NeurIPS 2022 Trading Complexity for Sparsity in Random Forest Explanations AAAI 2022 Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four ICML 2022 Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate AAAI 2022 Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space EMNLP 2022 Transformer Language Models without Positional Encodings Still Learn Positional Information EMNLP 2022 Transformer Uncertainty Estimation with Hierarchical Stochastic Attention AAAI 2022 Translation Error Detection as Rationale Extraction ACL 2022 Transparency, Detection and Imitation in Strategic Classification IJCAI 2022 Transparent Semantic Parsing with Universal Dependencies Using Graph Transformations COLING 2022 Tsetlin Machine for Solving Contextual Bandit Problems NeurIPS 2022 UC3M-PUCPR at SemEval-2022 Task 11: An Ensemble Method of Transformer-based Models for Complex Named Entity Recognition SemEval 2022 UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA AACL 2022 Uncertainty Calibration for Deep Audio Classifiers Interspeech 2022 Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models ACL 2022 Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis EMNLP 2022 Uncovering Surprising Event Boundaries in Narratives NAACL 2022 Understanding Game-Playing Agents with Natural Language Annotations ACL 2022 Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspective NeurIPS 2022 Understanding Robust Learning through the Lens of Representation Similarities NeurIPS 2022 Unified Auto Clinical Scoring (Uni-ACS) with Interpretable ML models MLHC 2022 Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction AAAI 2022 UNIREX: A Unified Learning Framework for Language Model Rationale Extraction ACL 2022