{"total":51,"rows":[{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"area":null},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109,"area":null},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2112.04417","title":"What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods","created":"2021-12-06","cited_by_count":98,"area":null},{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"area":null},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2206.10847","title":"Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI","created":"2022-06-22","cited_by_count":40,"area":null},{"id":"2202.07728","title":"Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis","created":"2022-02-15","cited_by_count":38,"area":null},{"id":"2104.08782","title":"On the Sensitivity and Stability of Model Interpretations in NLP","created":"2021-04-18","cited_by_count":30,"area":null},{"id":"2106.14648","title":"On Locality of Local Explanation Models","created":"2021-06-24","cited_by_count":25,"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":"2211.05667","title":"What Makes a Good Explanation?: A Harmonized View of Properties of Explanations","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2401.08552","title":"Explaining Time Series via Contrastive and Locally Sparse Perturbations","created":"2024-01-16","cited_by_count":22,"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":"2310.01820","title":"Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks","created":"2023-10-03","cited_by_count":17,"area":null},{"id":"2205.12423","title":"Deletion and Insertion Tests in Regression Models","created":"2022-05-25","cited_by_count":14,"area":null},{"id":"2408.03915","title":"Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation","created":"2024-08-07","cited_by_count":11,"area":null},{"id":"2309.16223","title":"GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanations","created":"2023-09-28","cited_by_count":9,"area":null},{"id":"2406.17224","title":"Large Language Models are Interpretable Learners","created":"2024-06-25","cited_by_count":7,"area":null},{"id":"2206.06854","title":"On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective","created":"2022-06-14","cited_by_count":6,"area":null},{"id":"2210.02419","title":"Boundary-Aware Uncertainty for Feature Attribution Explainers","created":"2022-10-05","cited_by_count":6,"area":null},{"id":"2305.03601","title":"Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models","created":"2023-05-05","cited_by_count":6,"area":null},{"id":"2211.04780","title":"On the Robustness of Explanations of Deep Neural Network Models: A Survey","created":"2022-11-09","cited_by_count":5,"area":null},{"id":"2310.03466","title":"The Blame Problem in Evaluating Local Explanations, and How to Tackle it","created":"2023-10-05","cited_by_count":5,"area":null},{"id":"2311.00858","title":"SmoothHess: ReLU Network Feature Interactions via Stein's Lemma","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2209.08647","title":"Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness","created":"2022-09-18","cited_by_count":4,"area":null},{"id":"2312.17591","title":"Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2507.18607","title":"Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents","created":"2025-07-24","cited_by_count":4,"area":"agents"},{"id":"2301.13845","title":"Interpreting Robustness Proofs of Deep Neural Networks","created":"2023-01-31","cited_by_count":3,"area":null},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2106.10947","title":"Leveraging Conditional Generative Models in a General Explanation Framework of Classifier Decisions","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2309.05679","title":"Good-looking but Lacking Faithfulness: Understanding Local Explanation Methods through Trend-based Testing","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2405.08468","title":"Challenges and Opportunities in Text Generation Explainability","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2406.00116","title":"A Sim2Real Approach for Identifying Task-Relevant Properties in Interpretable Machine Learning","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2407.05616","title":"Explainable Image Recognition via Enhanced Slot-attention Based Classifier","created":"2024-07-08","cited_by_count":2,"area":null},{"id":"2409.17774","title":"Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2105.01517","title":"Where and When: Space-Time Attention for Audio-Visual Explanations","created":"2021-05-04","cited_by_count":1,"area":null},{"id":"2401.14938","title":"DAM: Diffusion Activation Maximization for 3D Global Explanations","created":"2024-01-26","cited_by_count":1,"area":"diffusion"},{"id":"2406.11534","title":"Inpainting the Gaps: A Novel Framework for Evaluating Explanation Methods in Vision Transformers","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2509.19921","title":"On the Fragility of Contribution Score Computation in Federated Learning","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2106.02488","title":"Evaluating Local Explanations using White-box Models","created":"2021-06-04","cited_by_count":0,"area":null},{"id":"2203.02295","title":"Evaluating Local Model-Agnostic Explanations of Learning to Rank Models with Decision Paths","created":"2022-03-04","cited_by_count":0,"area":null},{"id":"2509.21209","title":"Learning Conformal Explainers for Image Classifiers","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2512.06665","title":"Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods","created":"2025-12-07","cited_by_count":0,"area":null},{"id":"2512.12605","title":"Causal inference and model explainability tools for retail","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2605.15328","title":"From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.16905","title":"AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps","created":"2026-05-16","cited_by_count":0,"area":null}],"next_cursor":null}