Interpretability

Pantypes: Diverse Representatives for Self-Explainable Models AAAI 2024 Parallel Backpropagation for Shared-Feature Visualization NeurIPS 2024 Parallel Empirical Evaluations: Resilience despite Concurrency AAAI 2024 Parameter-Efficient Generation of Natural Language Explanations for Chest X-ray Classification MIDL 2024 ParlaMint in TEITOK COLING 2024 PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation CVPR 2024 Partially Interpretable Models with Guarantees on Coverage and Accuracy ALT 2024 Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics NeurIPS 2024 Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models ICML 2024 PatentEval: Understanding Errors in Patent Generation NAACL 2024 Path Choice Matters for Clear Attributions in Path Methods ICLR 2024 Paths, Proofs, and Perfection: Developing a Human-Interpretable Proof System for Constrained Shortest Paths AAAI 2024 Pathwise Explanation of ReLU Neural Networks AISTATS 2024 Paying Attention to Deflections: Mining Pragmatic Nuances for Whataboutism Detection in Online Discourse ACL 2024 Paying attention to the words: explaining readability prediction for French as a foreign language COLING 2024 PEACH: Pretrained-Embedding Explanation across Contextual and Hierarchical Structure IJCAI 2024 PE: A Poincare Explanation Method for Fast Text Hierarchy Generation EMNLP 2024 PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck NAACL 2024 Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering ACL 2024 Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification EMNLP 2024 Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering NeurIPS 2024 Permutation-Based Hypothesis Testing for Neural Networks AAAI 2024 Personas as a Way to Model Truthfulness in Language Models EMNLP 2024 Perturbed examples reveal invariances shared by language models ACL 2024 P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains EMNLP 2024