{"total":88,"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":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"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":"2210.11584","title":"Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations","created":"2022-10-20","cited_by_count":85,"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":"2210.03735","title":"\"Help Me Help the AI\": Understanding How Explainability Can Support Human-AI Interaction","created":"2022-10-02","cited_by_count":63,"area":null},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2305.07722","title":"In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making","created":"2023-05-12","cited_by_count":50,"area":null},{"id":"2308.06248","title":"FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods","created":"2023-08-11","cited_by_count":50,"area":null},{"id":"2304.03916","title":"Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning","created":"2023-04-08","cited_by_count":47,"area":null},{"id":"2208.00780","title":"Visual correspondence-based explanations improve AI robustness and human-AI team accuracy","created":"2022-07-26","cited_by_count":39,"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":"2303.09224","title":"Human-AI Collaboration: The Effect of AI Delegation on Human Task Performance and Task Satisfaction","created":"2023-03-16","cited_by_count":32,"area":null},{"id":"2110.15355","title":"Explaining Latent Representations with a Corpus of Examples","created":"2021-10-28","cited_by_count":30,"area":null},{"id":"2205.05126","title":"A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Making","created":"2022-05-10","cited_by_count":29,"area":null},{"id":"2211.12380","title":"OCTET: Object-aware Counterfactual Explanations","created":"2022-11-22","cited_by_count":28,"area":null},{"id":"2306.06805","title":"Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization","created":"2023-06-11","cited_by_count":27,"area":null},{"id":"2302.10894","title":"Red Teaming Deep Neural Networks with Feature Synthesis Tools","created":"2023-02-08","cited_by_count":21,"area":"safety"},{"id":"2307.13566","title":"The Impact of Imperfect XAI on Human-AI Decision-Making","created":"2023-07-25","cited_by_count":21,"area":null},{"id":"2202.04092","title":"Machine Explanations and Human Understanding","created":"2022-02-08","cited_by_count":20,"area":null},{"id":"2412.12386","title":"Interpretable LLM-based Table Question Answering","created":"2024-12-16","cited_by_count":18,"area":null},{"id":"2205.01467","title":"On the Effect of Information Asymmetry in Human-AI Teams","created":"2022-05-03","cited_by_count":17,"area":null},{"id":"2307.14517","title":"The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers","created":"2023-07-26","cited_by_count":15,"area":null},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2305.08598","title":"Humans, AI, and Context: Understanding End-Users' Trust in a Real-World Computer Vision Application","created":"2023-05-15","cited_by_count":14,"area":null},{"id":"2405.01636","title":"Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Survey","created":"2024-05-02","cited_by_count":11,"area":null},{"id":"2503.06873","title":"Interactive Medical Image Analysis with Concept-based Similarity Reasoning","created":"2025-03-10","cited_by_count":11,"area":null},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2312.09783","title":"Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"id":"2205.13042","title":"How explainable are adversarially-robust CNNs?","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2303.17707","title":"Why is plausibility surprisingly problematic as an XAI criterion?","created":"2023-03-30","cited_by_count":9,"area":null},{"id":"2503.02003","title":"HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs","created":"2025-03-03","cited_by_count":9,"area":"lr"},{"id":"2510.11675","title":"FACE: Faithful Automatic Concept Extraction","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2309.08035","title":"Interpretability-Aware Vision Transformer","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2602.14869","title":"Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution","created":"2026-02-16","cited_by_count":8,"area":"mechinterp"},{"id":"2305.04073","title":"Explaining RL Decisions with Trajectories","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2506.14698","title":"Towards Desiderata-Driven Design of Visual Counterfactual Explainers","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2210.06725","title":"Assessing Out-of-Domain Language Model Performance from Few Examples","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2404.16042","title":"How explainable AI affects human performance: A systematic review of the behavioural consequences of saliency maps","created":"2024-04-03","cited_by_count":6,"area":null},{"id":"2505.18545","title":"B-score: Detecting biases in large language models using response history","created":"2025-05-24","cited_by_count":6,"area":null},{"id":"2309.13965","title":"May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainability","created":"2023-09-25","cited_by_count":5,"area":null},{"id":"2402.10039","title":"Feature Accentuation: Revealing 'What' Features Respond to in Natural Images","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2404.05238","title":"Allowing humans to interactively guide machines where to look does not always improve human-AI team's classification accuracy","created":"2024-04-08","cited_by_count":5,"area":null},{"id":"2407.05594","title":"SLIM: Spuriousness Mitigation with Minimal Human Annotations","created":"2024-07-08","cited_by_count":5,"area":null},{"id":"2407.19471","title":"On the Evaluation Consistency of Attribution-based Explanations","created":"2024-07-28","cited_by_count":5,"area":null},{"id":"2601.05328","title":"Bi-Orthogonal Factor Decomposition for Vision Transformers","created":"2026-01-08","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":"2302.06609","title":"Invisible Users: Uncovering End-Users' Requirements for Explainable AI via Explanation Forms and Goals","created":"2023-02-10","cited_by_count":4,"area":null},{"id":"2303.04809","title":"Learning Human-Compatible Representations for Case-Based Decision Support","created":"2023-03-06","cited_by_count":4,"area":null},{"id":"2305.02679","title":"Neighboring Words Affect Human Interpretation of Saliency Explanations","created":"2023-05-04","cited_by_count":4,"area":null},{"id":"2308.03161","title":"Precise Benchmarking of Explainable AI Attribution Methods","created":"2023-08-06","cited_by_count":4,"area":null},{"id":"2504.17023","title":"Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency maps","created":"2025-04-23","cited_by_count":4,"area":null},{"id":"2601.21851","title":"Visual Disentangled Diffusion Autoencoders: Scalable Counterfactual Generation for Foundation Models","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2307.09591","title":"Saliency strikes back: How filtering out high frequencies improves white-box explanations","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2308.13651","title":"PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans","created":"2023-08-25","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":"2208.08739","title":"Transcending XAI Algorithm Boundaries through End-User-Inspired Design","created":"2022-08-18","cited_by_count":2,"area":null},{"id":"2303.14608","title":"Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability","created":"2023-03-26","cited_by_count":2,"area":null},{"id":"2409.04116","title":"Segmentation and Smoothing Affect Explanation Quality More Than the Choice of Perturbation-based XAI Method for Image Explanations","created":"2024-09-06","cited_by_count":2,"area":null},{"id":"2412.12169","title":"Regulation of Language Models With Interpretability Will Likely Result In A Performance Trade-Off","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2412.18675","title":"TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models","created":"2024-12-24","cited_by_count":2,"area":"mllm"},{"id":"2504.10833","title":"Measuring the (Un)Faithfulness of Concept-Based Explanations","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2308.08949","title":"A Dual-Perspective Approach to Evaluating Feature Attribution Methods","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2407.21041","title":"They Look Like Each Other: Case-based Reasoning for Explainable Depression Detection on Twitter using Large Language Models","created":"2024-07-21","cited_by_count":1,"area":null},{"id":"2506.20267","title":"X-SiT: Inherently Interpretable Surface Vision Transformers for Dementia Diagnosis","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2507.06819","title":"Comprehensive Evaluation of Prototype Neural Networks","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2508.06742","title":"Learning Causal Structure Distributions for Robust Planning","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2211.14177","title":"Overcoming Catastrophic Forgetting by XAI","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2310.17949","title":"Instance Segmentation under Occlusions via Location-aware Copy-Paste Data Augmentation","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2405.13264","title":"Part-based Quantitative Analysis for Heatmaps","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2406.07702","title":"Graphical Perception of Saliency-based Model Explanations","created":"2024-06-11","cited_by_count":0,"area":null},{"id":"2406.10213","title":"Selecting Interpretability Techniques for Healthcare Machine Learning models","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2412.02275","title":"PCIM: Learning Pixel Attributions via Pixel-wise Channel Isolation Mixing in High Content Imaging","created":"2024-12-03","cited_by_count":0,"area":null},{"id":"2501.17328","title":"SIC: Similarity-Based Interpretable Image Classification with Neural Networks","created":"2025-01-28","cited_by_count":0,"area":null},{"id":"2505.07100","title":"Navigating the Rashomon Effect: How Personalization Can Help Adjust Interpretable Machine Learning Models to Individual Users","created":"2025-05-11","cited_by_count":0,"area":null},{"id":"2512.07578","title":"$\\phi$-Table: A Statistical Explanation for Global SHAP","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2603.20462","title":"Shift-Invariant Feature Attribution in the Application of Wireless Electrocardiograms","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.25251","title":"Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.04456","title":"Empirical Characterization of Rationale Stability Under Controlled Perturbations for Explainable Pattern Recognition","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2605.23080","title":"The Attribution Contract for Generative Language Models","created":"2026-05-21","cited_by_count":0,"area":"moe"},{"id":"2605.29983","title":"Improving Adversarial Robustness of Attribution via Implicit Regularization","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.07264","title":"Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanation","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2609.05399","title":"From Interpretability Methods to Interpretable Models","created":"2026-09-04","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},{"id":"2610.02673","title":"Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}