interpretability analysis

Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention Discriminability CVPR 2026 A Knowledge Distillation-Based Approach to Enhance Transparency of Classifier Models AAAI 2025 Can Transformers Do Enumerative Geometry? ICLR 2025 Disentangling Language and Culture for Evaluating Multilingual Large Language Models ACL 2025 Disentangling Linguistic Features with Dimension-Wise Analysis of Vector Embeddings NAACL 2025 Interpreting the Effects of Quantization on LLMs IJCNLP 2025 Mind the Inclusivity Gap: Multilingual Gender-Neutral Translation Evaluation with mGeNTE EMNLP 2025 Pattern Recognition or Medical Knowledge? The Problem with Multiple-Choice Questions in Medicine ACL 2025 Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement ACL 2025 Rethinking the Construction of Effective Metrics for Understanding the Mechanisms of Pretrained Language Models EMNLP 2023 Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments ACL 2022 Adversarial Robustness Guarantees for Classification with Gaussian Processes AISTATS 2020 Analysing Neural Language Models: Contextual Decomposition Reveals Default Reasoning in Number and Gender Assignment CoNLL 2019