{"total":32,"rows":[{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"area":null},{"id":"2111.02398","title":"Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods","created":"2021-11-01","cited_by_count":83,"area":null},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42,"area":null},{"id":"2303.00885","title":"Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision","created":"2023-03-02","cited_by_count":27,"area":null},{"id":"2206.04394","title":"Xplique: A Deep Learning Explainability Toolbox","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2202.12451","title":"Human-Centered Concept Explanations for Neural Networks","created":"2022-02-25","cited_by_count":23,"area":null},{"id":"2208.14966","title":"Concept Gradient: Concept-based Interpretation Without Linear Assumption","created":"2022-08-31","cited_by_count":20,"area":null},{"id":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2311.15303","title":"Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement","created":"2023-11-26","cited_by_count":10,"area":null},{"id":"2404.18533","title":"Evaluating Readability and Faithfulness of Concept-based Explanations","created":"2024-04-29","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":"2403.14566","title":"A survey on Concept-based Approaches For Model Improvement","created":"2024-03-21","cited_by_count":8,"area":null},{"id":"2311.15438","title":"ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]","created":"2023-11-26","cited_by_count":7,"area":null},{"id":"2402.01408","title":"Counterfactual Concept Bottleneck Models","created":"2024-02-02","cited_by_count":7,"area":null},{"id":"2207.01059","title":"Identifying the Context Shift between Test Benchmarks and Production Data","created":"2022-07-03","cited_by_count":5,"area":null},{"id":"2312.00192","title":"Benchmarking and Enhancing Disentanglement in Concept-Residual Models","created":"2023-11-30","cited_by_count":5,"area":null},{"id":"2409.12952","title":"The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanations","created":"2024-09-19","cited_by_count":5,"area":null},{"id":"2301.06324","title":"Img2Tab: Automatic Class Relevant Concept Discovery from StyleGAN Features for Explainable Image Classification","created":"2023-01-16","cited_by_count":4,"area":null},{"id":"2206.09046","title":"Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2207.11231","title":"Learning Unsupervised Hierarchies of Audio Concepts","created":"2022-07-21","cited_by_count":3,"area":null},{"id":"2402.14469","title":"Reimagining Anomalies: What If Anomalies Were Normal?","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2407.01331","title":"Restyling Unsupervised Concept Based Interpretable Networks with Generative Models","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2507.11099","title":"A Survey on Interpretability in Visual Recognition","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2210.09015","title":"Explaining Image Classification with Visual Debates","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2311.01609","title":"Responsible Emergent Multi-Agent Behavior","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2403.03704","title":"Causal Prototype-inspired Contrast Adaptation for Unsupervised Domain Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagery","created":"2024-03-06","cited_by_count":1,"area":null},{"id":"2502.11509","title":"DifCluE: Generating Counterfactual Explanations with Diffusion Autoencoders and modal clustering","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2408.03771","title":"Methodological Explainability Evaluation of an Interpretable Deep Learning Model for Post-Hepatectomy Liver Failure Prediction Incorporating Counterfactual Explanations and Layerwise Relevance Propagation: A Prospective In Silico Trial","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2412.11205","title":"Concept Learning in the Wild: Towards Algorithmic Understanding of Neural Networks","created":"2024-12-15","cited_by_count":0,"area":null},{"id":"2504.05254","title":"Explaining Low Perception Model Competency with High-Competency Counterfactuals","created":"2025-04-07","cited_by_count":0,"area":null}],"next_cursor":null}