Interpretability

Make it SING: Analyzing Semantic Invariants in Classifiers CVPR 2026 Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning AAAI 2026 Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing ACL 2026 Make Model Transparent: Brain Network Analysis via Causal and Knowledge Graph Learning AAAI 2026 Making Sense of LLM Decisions: A Prototype-based Framework for Explainable Classification AAAI 2026 Mary, the Cheeseburger-Eating Vegetarian: Do LLMs Recognize Incoherence in Narratives? EACL 2026 Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness ACL 2026 Measuring and Mitigating Shortcut Reliance in Language Models with Probe-Based Representation Entanglement ACL 2026 Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics? EACL 2026 Measuring the (Un)Faithfulness of Concept-Based Explanations CVPR 2026 Measuring the Unmeasurable: Unveiling Latent Cognitive Capabilities of LLM AAAI 2026 Mechanisms of Object Localization in Vision-Language Models CVPR 2026 Mechanisms of Prompt-Induced Hallucination in Vision–Language Models ACL 2026 Mechanistic Analysis Of Universality: Numerical Comparison Circuits Across Transformer Architectures ACL 2026 Mechanistic Interpretability of Animacy Effects on Structure Choice in GPT-2 CoNLL 2026 Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders ACL 2026 mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval WACV 2026 MEVER: Multi-Modal and Explainable Claim Verification with Graph-based Evidence Retrieval EACL 2026 Mind the Gap: Benchmarking LLM Uncertainty and Calibration with Specialty-Aware Clinical QA and Reasoning-Based Behavioural Features EACL 2026 Mind the Gap: Quantifying and Aligning Human-AI Visual Attention for Accident Anticipation AAAI 2026 MIRA: Evaluating Multimodal AI on Complex Clinical Reasoning in Interventional Radiology AAAI 2026 MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror Crafting AAAI 2026 Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering AAAI 2026 Mitigating Entity Hallucinations in 3D Radiology Report Generation via Dual-Stream Alignment AAAI 2026 Mitigating Hallucinations in Large Language Models via Causal Reasoning AAAI 2026