Interpretability

FastSHAP: Real-Time Shapley Value Estimation ICLR 2022 FAtNet: Cost-Effective Approach Towards Mitigating the Linguistic Bias in Speaker Verification Systems NAACL 2022 F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling WACV 2022 FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation NeurIPS 2022 Finding Badly Drawn Bunnies CVPR 2022 Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks ICLR 2022 Finding Skill Neurons in Pre-trained Transformer-based Language Models EMNLP 2022 First is Better Than Last for Language Data Influence NeurIPS 2022 Fixing Model Bugs with Natural Language Patches EMNLP 2022 Flexible Instance-Specific Rationalization of NLP Models AAAI 2022 FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles AAAI 2022 Formalizing Consistency and Coherence of Representation Learning NeurIPS 2022 Framework for Evaluating Faithfulness of Local Explanations ICML 2022 Frequency-Driven Imperceptible Adversarial Attack on Semantic Similarity CVPR 2022 FR: Folded Rationalization with a Unified Encoder NeurIPS 2022 From BERT‘s Point of View: Revealing the Prevailing Contextual Differences ACL 2022 From qualifiers to quantifiers: semantic shift at the paradigm level ACL 2022 Full-Text Argumentation Mining on Scientific Publications AACL 2022 Fuzzy Learning Machine NeurIPS 2022 Garden Path Traversal in GPT-2 EMNLP 2022 Gendered Mental Health Stigma in Masked Language Models EMNLP 2022 Generic Overgeneralization in Pre-trained Language Models COLING 2022 GlanceNets: Interpretable, Leak-proof Concept-based Models NeurIPS 2022 GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers NAACL 2022 GrammarSHAP: An Efficient Model-Agnostic and Structure-Aware NLP Explainer ACL 2022