Interpretability

Defeating Cerberus: Privacy-Leakage Mitigation in Vision Language Models EACL 2026 DeformTrace: A Deformable State Space Model with Relay Tokens for Temporal Forgery Localization AAAI 2026 DEFT: Demystifying VLN Failures via a Unified Dual-View Explainability Framework for LLM-based Agents ACL 2026 Delphi: A Neuro-Symbolic Framework for Individualized, Safe and Interpretable Treatment Recommendation AAAI 2026 Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models EACL 2026 Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering EACL 2026 Detecting (Un)answerability in Large Language Models with Linear Directions EACL 2026 Detection of Adversarial Prompts with Model Predictive Entropy EACL 2026 DeVisE: Towards the Behavioral Testing of Medical Large Language Models EACL 2026 Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning WACV 2026 Diagnosing Vision Language Models’ Perception by Leveraging Human Methods for Color Vision Deficiencies EACL 2026 Diagnosis of Dysarthria Severity and Explanation Generation Using XAI-Enhanced CLINIC-GENIE on Diadochokinetic Tasks EACL 2026 Difference in Task Performance on Sparse Speech Representations ACL 2026 Differentiated Directional Intervention: A Framework for Evading LLM Safety Alignment AAAI 2026 Diffusion-CAM: Faithful Visual Explanations for dMLLMs ACL 2026 Diffusion for Combating the Hallucination in Large Language Models (Student Abstract) AAAI 2026 Digital Forensic AI You Can Explain: A Case Study on Video Source Camera Identification WACV 2026 Direct Visual Grounding by Directing Attention of Visual Tokens WACV 2026 Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models ACL 2026 Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views ACL 2026 Discovering Decoupled Functional Modules in Large Language Models AAAI 2026 Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models ACL 2026 Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier AAAI 2026 Do Generative Video Models Understand Physical Principles? WACV 2026 Do Language Models Associate Sound with Meaning? A Multimodal Study of Sound Symbolism AAAI 2026