Interpretability

A Fine Line Between Irony and Sincerity: Identifying Bias in Transformer Models for Irony Detection ACL 2023 A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check EMNLP 2023 AGAIN: Adversarial Training With Attribution Span Enlargement and Hybrid Feature Fusion CVPR 2023 A Hierarchical Explanation Generation Method Based on Feature Interaction Detection ACL 2023 A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation NeurIPS 2023 Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness ICLR 2023 A Logic-based Approach to Contrastive Explainability for Neurosymbolic Visual Question Answering IJCAI 2023 AmbiCoref: Evaluating Human and Model Sensitivity to Ambiguous Coreference EACL 2023 Ambiguity Meets Uncertainty: Investigating Uncertainty Estimation for Word Sense Disambiguation ACL 2023 A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis EMNLP 2023 A Metadata-Driven Approach to Understand Graph Neural Networks NeurIPS 2023 A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization MLHC 2023 AMR Parsing is Far from Solved: GrAPES, the Granular AMR Parsing Evaluation Suite EMNLP 2023 A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification ICLR 2023 An Additive Instance-Wise Approach to Multi-class Model Interpretation ICLR 2023 Analyzing and Diagnosing Pose Estimation With Attributions CVPR 2023 Analyzing Pre-trained and Fine-tuned Language Models EMNLP 2023 Analyzing Transformers in Embedding Space ACL 2023 A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference NeurIPS 2023 A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection EMNLP 2023 An Integrated Approach for Political Bias Prediction and Explanation Based on Discursive Structure ACL 2023 An Operator Theoretic Approach for Analyzing Sequence Neural Networks AAAI 2023 A Novel Interpretable and Generalizable Re-synchronization Model for Cued Speech based on a Multi-Cuer Corpus Interspeech 2023 APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection EMNLP 2023 Approximating probabilistic explanations via supermodular minimization UAI 2023