Interpretability

Beyond Manual Transcripts: The Potential of Automated Speech Recognition Errors in Improving Alzheimer’s Disease Detection Interspeech 2025 Bringing Interpretability to Neural Audio Codecs Interspeech 2025 Can Transformers Do Enumerative Geometry? ICLR 2025 Designing and Contextualising Probes for African Languages ACL 2025 Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation CVPR 2025 Gaussian Smoothing in Saliency Maps: The Stability-Fidelity Trade-Off in Neural Network Interpretability AISTATS 2025 Graph Segmentation and Contrastive Enhanced Explainer for Graph Neural Networks AAAI 2025 ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs ACL 2025 Improving LLM Reasoning through Interpretable Role-Playing Steering EMNLP 2025 Interpretable Image Classification via Non-parametric Part Prototype Learning CVPR 2025 Interpreting Object-level Foundation Models via Visual Precision Search CVPR 2025 JoPA: Explaining Large Language Model’s Generation via Joint Prompt Attribution ACL 2025 LLMs Don’t Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations EMNLP 2025 LMO: Linear Mamba Operator for MRI Reconstruction CVPR 2025 Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models EMNLP 2025 On the Computational Tractability of the (Many) Shapley Values AISTATS 2025 Position-aware Automatic Circuit Discovery ACL 2025 Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing ACL 2025 TokenShapley: Token Level Context Attribution with Shapley Value ACL 2025 TRACE: Training and Inference-Time Interpretability Analysis for Language Models EMNLP 2025 A Convolutional Neural Network Interpretable Framework for Human Ventral Visual Pathway Representation AAAI 2024 Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable? NeurIPS 2024 Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model NeurIPS 2024 Dissenting Explanations: Leveraging Disagreement to Reduce Model Overreliance AAAI 2024 Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing their Contributions CVPR 2024