model interpretability

CohEx: A Generalized Framework for Cohort Explanation AAAI 2025 Cooperative or Competitive? Understanding the Interaction between Attention Heads From A Game Theory Perspective ACL 2025 COSMIC: Generalized Refusal Direction Identification in LLM Activations ACL 2025 Cyclic Vision-Language Manipulator: Towards Reliable and Fine-Grained Image Interpretation for Automated Report Generation IJCAI 2025 Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis ACL 2025 Demystifying optimized prompts in language models EMNLP 2025 Depression Detection on Social Media with Large Language Models EMNLP 2025 Dialz: A Python Toolkit for Steering Vectors ACL 2025 Different Speech Translation Models Encode and Translate Speaker Gender Differently ACL 2025 Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms EMNLP 2025 Do ImageNet-trained Models Learn Shortcuts? The Impact of Frequency Shortcuts on Generalization CVPR 2025 Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations? ICLR 2025 Endowing Interpretability for Neural Cognitive Diagnosis by Efficient Kolmogorov-Arnold Networks IJCAI 2025 Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework NAACL 2025 Explainable Saliency: Articulating Reasoning with Contextual Prioritization CVPR 2025 Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Property IJCAI 2025 Explaining Differences Between Model Pairs in Natural Language through Sample Learning EMNLP 2025 FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Datasets Dependency ACL 2025 Fast Explanations via Policy Gradient-Optimized Explainer IJCAI 2025 From Imitation to Introspection: Probing Self-Consciousness in Language Models ACL 2025 From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errors EMNLP 2025 HateBRXplain: A Benchmark Dataset with Human-Annotated Rationales for Explainable Hate Speech Detection in Brazilian Portuguese COLING 2025 HEARTS: A Holistic Framework for Explainable, Sustainable and Robust Text Stereotype Detection IJCNLP 2025 Higher Order Structures for Graph Explanations AAAI 2025 How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders EMNLP 2025