{"total":18,"rows":[{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243,"area":null},{"id":"2301.11911","title":"Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees","created":"2023-01-27","cited_by_count":50,"area":null},{"id":"2408.08041","title":"The Clever Hans Effect in Unsupervised Learning","created":"2024-08-15","cited_by_count":24,"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":"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":"2507.07544","title":"Position: We Need An Algorithmic Understanding of Generative AI","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2405.17523","title":"Locally Testing Model Detections for Semantic Global Concepts","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2411.19700","title":"Multi-Depth Concept Extraction for Post-Hoc Vision Encoder Explanation","created":"2024-11-29","cited_by_count":2,"area":null},{"id":"2505.06123","title":"Wasserstein Distances Made Explainable: Insights Into Dataset Shifts and Transport Phenomena","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2509.15198","title":"Explaining deep learning for ECG using time-localized clusters","created":"2025-09-18","cited_by_count":2,"area":null},{"id":"2511.03725","title":"Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition","created":"2025-11-05","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":"2404.14271","title":"Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation","created":"2024-04-22","cited_by_count":1,"area":null},{"id":"2403.07486","title":"XpertAI: uncovering regression model strategies for sub-manifolds","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2504.08553","title":"Uncovering the Structure of Explanation Quality with Spectral Analysis","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2609.18049","title":"Regional Explanations via Causal Sufficiency and Necessity","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.00895","title":"Towards Fast and Disentangled Counterfactuals for Visual Foundation Models","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}