Interpretability

Detecting Omissions in LLM-Generated Medical Summaries EMNLP 2025 Detecting Sexism in Tweets: A Sentiment Analysis and Graph Neural Network Approach NAACL 2025 Deterministic Object Pose Confidence Region Estimation ICCV 2025 Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation Service NAACL 2025 Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens CVPR 2025 DGExplainer: Explaining Dynamic Graph Neural Networks via Relevance Back-propagation IJCAI 2025 Diagnosing Failures in Large Language Models’ Answers: Integrating Error Attribution into Evaluation Framework ACL 2025 Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time EMNLP 2025 Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization EMNLP 2025 Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties EMNLP 2025 Dialz: A Python Toolkit for Steering Vectors ACL 2025 DiffCAM: Data-Driven Saliency Maps by Capturing Feature Differences CVPR 2025 Differentiable Optimization of Similarity Scores Between Models and Brains ICLR 2025 Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-Based Human Activity Recognition WACV 2025 Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient ICLR 2025 Different Speech Translation Models Encode and Translate Speaker Gender Differently ACL 2025 Diffusion Models for Attribution AAAI 2025 DiL: An Explainable and Practical Metric for Abnormal Uncertainty in Object Detection WACV 2025 DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning EMNLP 2025 DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery CVPR 2025 DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement EMNLP 2025 Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization NAACL 2025 Discourse Heuristics For Paradoxically Moral Self-Correction EMNLP 2025 Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning CVPR 2025 Discovering Influential Neuron Path in Vision Transformers ICLR 2025