Skip to content
conftrace_

Interpretability

8,292 papers

5
14
512
2,137
'10
'15
'20
'25

Papers

Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling NeurIPS 2021 Plan Explanations that Exploit a Cognitive Spatial Model ACL 2021 Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models ACL 2021 PopSkipJump: Decision-Based Attack for Probabilistic Classifiers ICML 2021 Practical Relative Order Attack in Deep Ranking ICCV 2021 Predicting Discourse Trees from Transformer-based Neural Summarizers NAACL 2021 Predicting Inductive Biases of Pre-Trained Models ICLR 2021 Prevent the Language Model from being Overconfident in Neural Machine Translation ACL 2021 Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignments ACL 2021 Probabilistic Sufficient Explanations IJCAI 2021 Probing Commonsense Explanation in Dialogue Response Generation EMNLP 2021 Probing Contextual Language Models for Common Ground with Visual Representations NAACL 2021 Probing for Bridging Inference in Transformer Language Models NAACL 2021 Probing Pre-trained Language Models for Semantic Attributes and their Values EMNLP 2021 Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance? EACL 2021 ProSPer: Probing Human and Neural Network Language Model Understanding of Spatial Perspective EMNLP 2021 Provably efficient, succinct, and precise explanations NeurIPS 2021 pRSL: Interpretable multi-label stacking by learning probabilistic rules UAI 2021 Putting Words in BERT’s Mouth: Navigating Contextualized Vector Spaces with Pseudowords EMNLP 2021 Quantifying Explainers of Graph Neural Networks in Computational Pathology CVPR 2021 RADAR-X: An Interactive Interface Pairing Contrastive Explanations with Revised Plan Suggestions AAAI 2021 Rationales for Sequential Predictions EMNLP 2021 Raven's Progressive Matrices Completion with Latent Gaussian Process Priors AAAI 2021 ReAct: Out-of-distribution Detection With Rectified Activations NeurIPS 2021 Realistic Evaluation Principles for Cross-document Coreference Resolution ACL 2021