Interpretability

Discovering Symbolic Cognitive Models from Human and Animal Behavior ICML 2025 Discrete Subgraph Sampling for Interpretable Graph based Visual Question Answering COLING 2025 Discriminating image representations with principal distortions ICLR 2025 Discursive Circuits: How Do Language Models Understand Discourse Relations? EMNLP 2025 Disentangled Table-Graph Representation for Interpretable Transmission Line Fault Location AAAI 2025 Disentangling Language and Culture for Evaluating Multilingual Large Language Models ACL 2025 Disentangling Language Understanding and Reasoning Structures in Cross-lingual Chain-of-Thought Prompting EMNLP 2025 Disentangling Linguistic Features with Dimension-Wise Analysis of Vector Embeddings NAACL 2025 Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities ACL 2025 Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms EMNLP 2025 Disentangling Memory and Reasoning Ability in Large Language Models ACL 2025 Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability CVPR 2025 Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study EMNLP 2025 Dissecting Persona-Driven Reasoning in Language Models via Activation Patching EMNLP 2025 Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies ICML 2025 Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms ICML 2025 Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers ICLR 2025 Distributional Counterfactual Explanations With Optimal Transport AISTATS 2025 Distributional Surgery for Language Model Activations EMNLP 2025 Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification CVPR 2025 Divide, Discover, Deploy: Factorized Skill Learning with Symmetry and Style Priors CoRL 2025 Divide-Solve-Combine: An Interpretable and Accurate Prompting Framework for Zero-shot Multi-Intent Detection AAAI 2025 DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains EMNLP 2025 DME-Driver: Integrating Human Decision Logic and 3D Scene Perception in Autonomous Driving AAAI 2025 Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms EMNLP 2025