Interpretability

Do Large Language Models Reason About Uncertainty Like Humans? A Benchmark on Hurricane Forecast Visualization Comprehension AAAI 2026 Do Large Language Models Think like the Brain? Sentence-Level Evidences from Layer-Wise Embeddings and fMRI AAAI 2026 Do LLMs Encode Functional Importance of Reasoning Tokens ? ACL 2026 Do LLMs model human linguistic variation? A case study in Hindi-English Verb code-mixing EACL 2026 Don’t Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation EACL 2026 Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions CVPR 2026 Driving with Regulation: Trustworthy and Interpretable Decision-Making for Autonomous Driving with Retrieval-Augmented Reasoning AAAI 2026 DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models ACL 2026 DuwatBench: Bridging Language and Visual Heritage through an Arabic Calligraphy Benchmark for Multimodal Understanding EACL 2026 Early-Exit and Instant Confidence Translation Quality Estimation EACL 2026 EduMod-LLM: A Modular Approach for Designing Flexible and Transparent Educational Assistants AAAI 2026 Efficiently Computing Compact Formal Explanations AAAI 2026 Efficient Transcoder Adaptation for Fine-Tuned Models: Revealing Medical Reasoning Mechanisms in Large Language Models AAAI 2026 E-Logic Prompt: Unified Energy-Logic Framework for Continual Visual Question Answering AAAI 2026 Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models ACL 2026 Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers ACL 2026 Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale Verifier AAAI 2026 Empowering LLMs with Symbolic Representation and Reasoning AAAI 2026 ENCORE : A Neural Collapse Perspective on Out-of-Distribution Detection in Deep Neural Networks WACV 2026 Enhancing Chemical Explainability Through Counterfactual Masking AAAI 2026 Enhancing Interpretability for Vision Models via Shapley Value Optimization AAAI 2026 Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief AAAI 2026 EPIC: Explanation of Pretrained Image Classification Networks via Prototypes AAAI 2026 EvalSense: A Framework for Domain-Specific LLM (Meta-)Evaluation EACL 2026 Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders EACL 2026