Interpretability

FraudGNAM: Inherently Interpretable Spectral GNN for Graph Fraud Detection UAI 2026 From Attribution to Action: Jointly ALIGNing Predictions and Explanations AAAI 2026 From Decision Trees to Boolean Logic: A Fast and Unified SHAP Algorithm AAAI 2026 From Detection to Explanation: Modeling Fine-Grained Emotional Social Influence Techniques with LLMs and Human Preferences EACL 2026 From Factuality to Meta-Factivity: A Cognitive Blueprint for Trustworthy LLMs ACL 2026 From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models ACL 2026 From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts? ACL 2026 From Pixels to Histopathology: A Graph-Based Framework for Interpretable Whole Slide Image Analysis MIDL 2026 From Sampling to Cognition: Modeling Internal Cognitive Confidence in Language Models for Robust Uncertainty Calibration AAAI 2026 From Sentences to Proof Trees: Leveraging Language Models for Structured Reasoning EACL 2026 From Weights to Activations: Is Steering the Next Frontier of Adaptation? ACL 2026 FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI MIDL 2026 Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs EACL 2026 FUSE: Fine-Grained and Semantic-Aware Learning for Unified Image Understanding and Generation AAAI 2026 Fusing Deep Learning and Fuzzy Logic: A Framework for Adaptive and Scalable Interpretability AAAI 2026 Generating In-Distribution Counterfactual Explanation for Graph Neural Networks AAAI 2026 GenProve: Learning to Generate Text with Fine-Grained Provenance ACL 2026 Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signatures AAAI 2026 GKnow: Measuring the Entanglement of Gender Bias and Factual Gender ACL 2026 GLANCE: Global Actions in a Nutshell for Counterfactual Explainability AAAI 2026 GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization AAAI 2026 Global Information Thresholding for Sufficient and Necessary Circuits CVPR 2026 Global-Local Confidence Fusion for Hallucination Detection in Mathematical Reasoning Task AAAI 2026 GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs ACL 2026 Graph of Trace: Visualizing Execution Traces of Scientific Agents ACL 2026