Interpretability

A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation ACL 2022 A Tour of Explicit Multilingual Semantics: Word Sense Disambiguation, Semantic Role Labeling and Semantic Parsing AACL 2022 A Transition-based Method for Complex Question Understanding COLING 2022 Attack Agnostic Detection of Adversarial Examples via Random Subspace Analysis WACV 2022 AttCAT: Explaining Transformers via Attentive Class Activation Tokens NeurIPS 2022 Attention-based Interpretability with Concept Transformers ICLR 2022 AttExplainer: Explain Transformer via Attention by Reinforcement Learning IJCAI 2022 Attributable Visual Similarity Learning CVPR 2022 Attributing Fair Decisions with Attention Interventions NAACL 2022 Attribution of predictive uncertainties in classification models UAI 2022 AutoCAD: Automatically Generate Counterfactuals for Mitigating Shortcut Learning EMNLP 2022 Autoinverse: Uncertainty Aware Inversion of Neural Networks NeurIPS 2022 Automated Design of Grey-Box Recurrent Neural Networks For Fault Diagnosis using Structural Models and Causal Information L4DC 2022 Automatic Dialect Density Estimation for African American English Interspeech 2022 Automatic Rule Induction for Efficient Semi-Supervised Learning EMNLP 2022 Automatic scoring of short answers using justification cues estimated by BERT NAACL 2022 Automatized Detection and Annotation for Calls to Action in Latin-American Social Media Postings COLING 2022 AutoMS: Automatic Model Selection for Novelty Detection with Error Rate Control NeurIPS 2022 Auto-Physics-Encoder: Using Physics-Informed Latent Layer Two-Way Physics Flow for Monitoring Systems with Unobservability ACML 2022 Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning ICLR 2022 Axiomatic Foundations of Explainability IJCAI 2022 Axiomatization of Aggregates in Answer Set Programming AAAI 2022 A Zest of LIME: Towards Architecture-Independent Model Distances ICLR 2022 Azimuth: Systematic Error Analysis for Text Classification EMNLP 2022 Backdoor Attacks on the DNN Interpretation System AAAI 2022