feature attribution

Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors CVPR 2026 Beyond the Token: Correcting the Tokenization Bias in XAI via Morphologically-Aligned Projection EACL 2026 cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context UAI 2026 Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classification WACV 2026 Digital Forensic AI You Can Explain: A Case Study on Video Source Camera Identification WACV 2026 Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier AAAI 2026 Efficient Transcoder Adaptation for Fine-Tuned Models: Revealing Medical Reasoning Mechanisms in Large Language Models AAAI 2026 Exact Shapley Attributions in Quadratic-time for FANOVA Gaussian Processes AAAI 2026 Feature Attribution for Human Sensing with Radio Signals AAAI 2026 H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers CVPR 2026 Interpretable Reward Model via Sparse Autoencoder AAAI 2026 LAFaCT: Attribution-based Localization and Focused Sequential Analysis of Fact-Critical Tokens for Hallucination Detection ACL 2026 NEAT-IR: Neural Explainable Analysis Tool for Information Retrieval ACL 2026 On the Computational Tractability of Probabilistic Global and Local Sufficient Explanation AAAI 2026 PR-XAI: PageRank-Based Feature Attribution for Transformers ACL 2026 Rethinking Explanation Evaluation Under the Retraining Scheme AAAI 2026 Shapley Value Approximation Based on k-Additive Games AAAI 2026 Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation CVPR 2026 I^2AM: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps ICLR 2025 Accurate Estimation of Feature Importance Faithfulness for Tree Models AAAI 2025 Attention Consistency for LLMs Explanation EMNLP 2025 Axiomatic Explainer Globalness via Optimal Transport AISTATS 2025 BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation AAAI 2025 CafGa: Customizing Feature Attributions to Explain Language Models EMNLP 2025 CAM-Based Methods Can See through Walls (Extended Abstract) IJCAI 2025