model interpretability

Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision AAAI 2024 Interpretability-based Tailored Knowledge Editing in Transformers EMNLP 2024 Interpretable Mesomorphic Networks for Tabular Data NeurIPS 2024 Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE) NeurIPS 2024 Jump to Conclusions: Short-Cutting Transformers with Linear Transformations COLING 2024 Language Model as Visual Explainer NeurIPS 2024 LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks IJCAI 2024 Latent Concept-based Explanation of NLP Models EMNLP 2024 Learning Accurate and Interpretable Decision Trees UAI 2024 Learning to Understand: Identifying Interactions via the Möbius Transform NeurIPS 2024 Less is More: Fewer Interpretable Region via Submodular Subset Selection ICLR 2024 LLM Factoscope: Uncovering LLMs’ Factual Discernment through Measuring Inner States ACL 2024 LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study EMNLP 2024 MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction EMNLP 2024 MFABA: A More Faithful and Accelerated Boundary-Based Attribution Method for Deep Neural Networks AAAI 2024 Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics NeurIPS 2024 On Measuring Faithfulness or Self-consistency of Natural Language Explanations ACL 2024 On the Faithfulness of Vision Transformer Explanations CVPR 2024 On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods AAAI 2024 Out-of-distribution generalisation in spoken language understanding Interspeech 2024 Path Choice Matters for Clear Attributions in Path Methods ICLR 2024 PEACH: Pretrained-Embedding Explanation across Contextual and Hierarchical Structure IJCAI 2024 Plausible Extractive Rationalization through Semi-Supervised Entailment Signal ACL 2024 Pre-trained Large Language Models Use Fourier Features to Compute Addition NeurIPS 2024 Promoting Counterfactual Robustness through Diversity AAAI 2024