Interpretability

Comparing LLM-generated and human-authored news text using formal syntactic theory ACL 2025 Complexity of Injectivity and Verification of ReLU Neural Networks (Extended Abstract) COLT 2025 Compositional Generalisation for Explainable Hate Speech Detection EMNLP 2025 Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers CVPR 2025 Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detection NAACL 2025 Computation Mechanism Behind LLM Position Generalization ACL 2025 Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders ICML 2025 COMRECGC: Global Graph Counterfactual Explainer through Common Recourse ICML 2025 CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models AAAI 2025 Concept-Based Unsupervised Domain Adaptation ICML 2025 Concept Bottleneck Language Models For Protein Design ICLR 2025 Concept Bottleneck Large Language Models ICLR 2025 ConceptCarve: Dynamic Realization of Evidence ACL 2025 Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstraction NAACL 2025 Conceptual Diagnostics for Knowledge Graphs and Large Language Models ACL 2025 Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency WACV 2025 CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts ICLR 2025 Conditional Diffusion Models are Medical Image Classifiers that Provide Explainability and Uncertainty for Free MIDL 2025 Conditional Feature Importance with Generative Modeling Using Adversarial Random Forests AAAI 2025 Confidence Elicitation: A New Attack Vector for Large Language Models ICLR 2025 Conflicts in Texts: Data, Implications and Challenges EMNLP 2025 Conformal Language Model Reasoning with Coherent Factuality ICLR 2025 Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation CVPR 2025 ConKE: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning ACL 2025 Connecting Concept Layers and Rationales to Enhance Language Model Interpretability EMNLP 2025