{"total":31,"rows":[{"id":"2112.11407","title":"Toward Explainable AI for Regression Models","created":"2021-12-21","cited_by_count":31,"area":null},{"id":"2212.14855","title":"Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces","created":"2022-12-30","cited_by_count":25,"area":null},{"id":"2408.08041","title":"The Clever Hans Effect in Unsupervised Learning","created":"2024-08-15","cited_by_count":24,"area":null},{"id":"2408.00531","title":"ReSi: A Comprehensive Benchmark for Representational Similarity Measures","created":"2024-08-01","cited_by_count":19,"area":null},{"id":"2102.13519","title":"PredDiff: Explanations and Interactions from Conditional Expectations","created":"2021-02-26","cited_by_count":17,"area":null},{"id":"2406.04280","title":"xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology","created":"2024-06-06","cited_by_count":16,"area":null},{"id":"2203.01928","title":"Label-Free Explainability for Unsupervised Models","created":"2022-03-03","cited_by_count":14,"area":null},{"id":"2502.14862","title":"Interpretable Text Embeddings and Text Similarity Explanation: A Survey","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2401.17441","title":"Explaining Predictive Uncertainty by Exposing Second-Order Effects","created":"2024-01-30","cited_by_count":10,"area":null},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2304.05727","title":"Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks","created":"2023-04-12","cited_by_count":9,"area":null},{"id":"2405.06604","title":"Explaining Text Similarity in Transformer Models","created":"2024-05-10","cited_by_count":9,"area":null},{"id":"2206.09753","title":"Visualizing and Understanding Contrastive Learning","created":"2022-06-20","cited_by_count":7,"area":null},{"id":"2408.17198","title":"Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features","created":"2024-08-30","cited_by_count":7,"area":null},{"id":"2402.12118","title":"Sparse, Efficient and Explainable Data Attribution with DualXDA","created":"2024-02-19","cited_by_count":6,"area":null},{"id":"2107.02008","title":"Improving a neural network model by explanation-guided training for glioma classification based on MRI data","created":"2021-07-05","cited_by_count":5,"area":null},{"id":"2507.07544","title":"Position: We Need An Algorithmic Understanding of Generative AI","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2211.08425","title":"A Rigorous Study Of The Deep Taylor Decomposition","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2310.09091","title":"Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI","created":"2023-10-13","cited_by_count":3,"area":null},{"id":"2408.14153","title":"Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2511.05064","title":"Order-Level Attention Similarity Across Language Models: A Latent Commonality","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2603.08328","title":"Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2606.00557","title":"Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2605.23673","title":"Relevant Walk Search for Explaining Graph Neural Networks","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2106.10086","title":"It's FLAN time! Summing feature-wise latent representations for interpretability","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2510.10753","title":"Restricted Receptive Fields for Face Verification","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2510.18810","title":"When LRP Diverges from Leave-One-Out in Transformers","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2606.06224","title":"Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.14555","title":"Rethinking Global Average Pooling: Your Classifier Is Secretly a Multi-Instance Learner","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.28386","title":"Explaining Image Similarity with Automatically Extracted Concept Activation Vectors","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.14130","title":"AlignFace: Human-Aligned Face Similarity Metric with Interpretable Concept Relations","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}