Interpretability

Data Augmentation via Latent Diffusion for Saliency Prediction ECCV 2024 Data-Centric Explainable Debiasing for Improving Fairness in Pre-trained Language Models ACL 2024 Data Contamination Calibration for Black-box LLMs ACL 2024 Data-Driven Discovery of Design Specifications (Student Abstract) AAAI 2024 Data Efficient Paradigms for Personalized Assessment of Black-Box Taskable AI Systems AAAI 2024 Data-faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables NeurIPS 2024 Debiasing surgeon: fantastic weights and how to find them ECCV 2024 Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination? NAACL 2024 DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation ECCV 2024 Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning EMNLP 2024 Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models ECCV 2024 Decision-Focused Model-based Reinforcement Learning for Reward Transfer MLHC 2024 DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers NAACL 2024 Decoding AI’s Nudge: A Unified Framework to Predict Human Behavior in AI-Assisted Decision Making AAAI 2024 Decoding Probing: Revealing Internal Linguistic Structures in Neural Language Models Using Minimal Pairs COLING 2024 Decoding-Time Language Model Alignment with Multiple Objectives NeurIPS 2024 Decompose and Compare Consistency: Measuring VLMs’ Answer Reliability via Task-Decomposition Consistency Comparison EMNLP 2024 Decomposing and Editing Predictions by Modeling Model Computation ICML 2024 Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP NeurIPS 2024 Decomposing Co-occurrence Matrices into Interpretable Components as Formal Concepts ACL 2024 Decomposing Global Feature Effects Based on Feature Interactions JMLR 2024 Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling ICML 2024 Decorrelated Variable Importance JMLR 2024 DeepBern-Nets: Taming the Complexity of Certifying Neural Networks Using Bernstein Polynomial Activations and Precise Bound Propagation AAAI 2024 Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning EMNLP 2024