Interpretability

HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection EMNLP 2025 Hybrid Concept Bottleneck Models CVPR 2025 Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations ICML 2025 HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks ICLR 2025 Hyperdimensional Uncertainty Quantification for Multimodal Uncertainty Fusion in Autonomous Vehicles Perception CVPR 2025 IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck ICML 2025 ICLR: In-Context Learning of Representations ICLR 2025 ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs ACL 2025 ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models CVPR 2025 Identifying and Answering Questions with False Assumptions: An Interpretable Approach EMNLP 2025 Identifying Drivers of Predictive Aleatoric Uncertainty IJCAI 2025 Identifying Metric Structures of Deep Latent Variable Models ICML 2025 Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework EMNLP 2025 Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts AAAI 2025 Idola Tribus of AI: Large Language Models tend to perceive order where none exists EMNLP 2025 I-GUARD: Interpretability-Guided Parameter Optimization for Adversarial Defense EMNLP 2025 iLLuMinaTE: An LLM-XAI Framework Leveraging Social Science Explanation Theories Towards Actionable Student Performance Feedback AAAI 2025 Illuminating Logical Fallacies with the CAMPFIRE Corpus ACL 2025 Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inference CVPR 2025 Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection AAAI 2025 Importance-Guided Interpretability and Pruning for Video Transformers in Driver Action Recognition WACV 2025 Importance Sampling for Nonlinear Models ICML 2025 Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers EMNLP 2025 Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models NAACL 2025 Improve Language Model and Brain Alignment via Associative Memory ACL 2025