Interpretability

AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments EMNLP 2024 AVR: synergizing foundation models for audio-visual humor detection Interspeech 2024 AXCEL: Automated eXplainable Consistency Evaluation using LLMs EMNLP 2024 Axiomatic Aggregations of Abductive Explanations AAAI 2024 Backward Lens: Projecting Language Model Gradients into the Vocabulary Space EMNLP 2024 Backward Responsibility in Transition Systems Using General Power Indices AAAI 2024 Balancing Transparency and Accuracy: A Comparative Analysis of Rule-Based and Deep Learning Models in Political Bias Classification EMNLP 2024 Bayesian Knowledge Distillation: A Bayesian Perspective of Distillation with Uncertainty Quantification ICML 2024 Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning ICML 2024 BayOTIDE: Bayesian Online Multivariate Time Series Imputation with Functional Decomposition ICML 2024 B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable NeurIPS 2024 BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts UAI 2024 Benchmark Generation Framework With Customizable Distortions for Image Classifier Robustness WACV 2024 Benchmarking Cognitive Biases in Large Language Models as Evaluators ACL 2024 Benchmarking Cyber Harassment Dialogue Comprehension through Emotion-Informed Manifestations-Determinants Demarcation AAAI 2024 Benchmarking Deletion Metrics with the Principled Explanations ICML 2024 Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex. NeurIPS 2024 Benchmarking the Attribution Quality of Vision Models NeurIPS 2024 Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks NeurIPS 2024 Beta-LR: Interpretable Logical Reasoning based on Beta Distribution NAACL 2024 Better Explain Transformers by Illuminating Important Information EACL 2024 Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling AAAI 2024 Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales NeurIPS 2024 Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain ICLR 2024 Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals EMNLP 2024