Interpretability

A Causal Lens for Evaluating Faithfulness Metrics EMNLP 2025 Accurate Estimation of Feature Importance Faithfulness for Tree Models AAAI 2025 Accurate Identification of Communication Between Multiple Interacting Neural Populations ICML 2025 Accurate Nucleic Acid-Binding Residue Identification Based Domain-Adaptive Protein Language Model and Explainable Geometric Deep Learning AAAI 2025 A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing ICML 2025 A Classification View on Meta Learning Bandits ICML 2025 A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models EMNLP 2025 A Compliance Checking Framework Based on Retrieval Augmented Generation COLING 2025 A Conformal Risk Control Framework for Granular Word Assessment and Uncertainty Calibration of CLIPScore Quality Estimates ACL 2025 ActionReasoningBench: Reasoning about Actions with and without Ramification Constraints ICLR 2025 Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks ICLR 2025 Activation Steering Decoding: Mitigating Hallucination in Large Vision-Language Models through Bidirectional Hidden State Intervention ACL 2025 Activation Subspaces for Out-of-Distribution Detection ICCV 2025 Active feature acquisition via explainability-driven ranking ICML 2025 Active Fourier Auditor for Estimating Distributional Properties of ML Models AAAI 2025 Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning. ICCV 2025 Adaptively profiling models with task elicitation EMNLP 2025 Adaptive Platt Scaling with Causal Interpretations for Self-Reflective Language Model Uncertainty Estimates EMNLP 2025 Adaptive Retention & Correction: Test-Time Training for Continual Learning ICLR 2025 Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home ACL 2025 AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence ICML 2025 Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers ICLR 2025 AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender EMNLP 2025 Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs EMNLP 2025 Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization ICML 2025