Interpretability

No Questions are Stupid, but some are Poorly Posed: Understanding Poorly-Posed Information-Seeking Questions ACL 2025 NormXLogit: The Head-on-Top Never Lies EMNLP 2025 On Relation-Specific Neurons in Large Language Models EMNLP 2025 Position-aware Automatic Circuit Discovery ACL 2025 Probabilistic Explanations for Linear Models AAAI 2025 Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks ACL 2025 Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis CVPR 2025 ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation AAAI 2025 ProtoLens: Advancing Prototype Learning for Fine-Grained Interpretability in Text Classification ACL 2025 ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering EMNLP 2025 Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time CVPR 2025 Reliable and Scalable Variable Importance Estimation via Warm-start and Early Stopping AISTATS 2025 ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques AAAI 2025 Serial Position Effects of Large Language Models ACL 2025 Social Good or Scientific Curiosity? Uncovering the Research Framing Behind NLP Artefacts EMNLP 2025 Sparse Activation Editing for Reliable Instruction Following in Narratives EMNLP 2025 Targeted Learning for Variable Importance UAI 2025 Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition CVPR 2025 Towards Trustable SHAP Scores AAAI 2025 Tuning-Free Accountable Intervention for LLM Deployment – a Metacognitive Approach AAAI 2025 Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory AISTATS 2025 Unlocking Better Closed-Set Alignment Based on Neural Collapse for Open-Set Recognition AAAI 2025 Unsupervised Hallucination Detection by Inspecting Reasoning Processes EMNLP 2025 Using Shapley interactions to understand how models use structure ACL 2025 Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models AAAI 2025