{"total":365,"rows":[{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2202.06861","title":"Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond","created":"2022-02-14","cited_by_count":171,"area":null},{"id":"2210.13966","title":"The Debate Over Understanding in AI's Large Language Models","created":"2022-10-14","cited_by_count":142,"area":null},{"id":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136,"area":null},{"id":"2112.03052","title":"Scaling Up Influence Functions","created":"2021-12-06","cited_by_count":132,"area":null},{"id":"2310.19775","title":"Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions","created":"2023-10-30","cited_by_count":125,"area":null},{"id":"2105.00304","title":"SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects","created":"2021-05-01","cited_by_count":104,"area":null},{"id":"2305.07141","title":"The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain","created":"2023-05-11","cited_by_count":101,"area":null},{"id":"2304.05653","title":"A Closer Look at the Explainability of Contrastive Language-Image Pre-training","created":"2023-04-12","cited_by_count":96,"area":"mllm"},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91,"area":null},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"area":null},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83,"area":null},{"id":"2103.05154","title":"Explanations in Autonomous Driving: A Survey","created":"2021-03-09","cited_by_count":81,"area":null},{"id":"2112.11561","title":"Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions","created":"2021-12-21","cited_by_count":73,"area":"driving"},{"id":"2402.15052","title":"ToMBench: Benchmarking Theory of Mind in Large Language Models","created":"2024-02-23","cited_by_count":72,"area":null},{"id":"2105.02968","title":"This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks","created":"2021-05-05","cited_by_count":65,"area":null},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65,"area":null},{"id":"2305.19951","title":"Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts","created":"2023-05-31","cited_by_count":63,"area":null},{"id":"2104.07411","title":"NICE: An Algorithm for Nearest Instance Counterfactual Explanations","created":"2021-04-15","cited_by_count":62,"area":null},{"id":"2103.04244","title":"Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications","created":"2021-03-07","cited_by_count":59,"area":null},{"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":"2311.11908","title":"Continual Learning: Applications and the Road Forward","created":"2023-11-20","cited_by_count":59,"area":null},{"id":"2106.13200","title":"Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy","created":"2021-06-24","cited_by_count":55,"area":null},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53,"area":null},{"id":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52,"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":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"area":null},{"id":"2212.03523","title":"Criteria for Classifying Forecasting Methods","created":"2022-12-07","cited_by_count":48,"area":null},{"id":"2208.08831","title":"Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning","created":"2022-08-18","cited_by_count":45,"area":null},{"id":"2108.12204","title":"This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation","created":"2021-08-27","cited_by_count":43,"area":null},{"id":"2104.12871","title":"Why AI is Harder Than We Think","created":"2021-04-26","cited_by_count":41,"area":null},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41,"area":null},{"id":"2401.04079","title":"RudolfV: A Foundation Model by Pathologists for Pathologists","created":"2024-01-08","cited_by_count":41,"area":null},{"id":"2402.12715","title":"The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning","created":"2024-02-20","cited_by_count":41,"area":null},{"id":"2210.06959","title":"A Survey on Explainable Anomaly Detection","created":"2022-10-13","cited_by_count":39,"area":null},{"id":"2306.04507","title":"Improving neural network representations using human similarity judgments","created":"2023-06-07","cited_by_count":38,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2107.07045","title":"Explainable AI: current status and future directions","created":"2021-07-12","cited_by_count":33,"area":null},{"id":"2302.01242","title":"Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal","created":"2023-02-02","cited_by_count":33,"area":null},{"id":"2311.13594","title":"Labeling Neural Representations with Inverse Recognition","created":"2023-11-22","cited_by_count":32,"area":null},{"id":"2406.07592","title":"MambaLRP: Explaining Selective State Space Sequence Models","created":"2024-06-11","cited_by_count":32,"area":"ssm"},{"id":"2506.23270","title":"Token Activation Map to Visually Explain Multimodal LLMs","created":"2025-06-29","cited_by_count":32,"area":"mllm"},{"id":"2112.11407","title":"Toward Explainable AI for Regression Models","created":"2021-12-21","cited_by_count":31,"area":null},{"id":"2205.12141","title":"One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks","created":"2022-05-24","cited_by_count":29,"area":null},{"id":"2206.05075","title":"Diffeomorphic Counterfactuals with Generative Models","created":"2022-06-10","cited_by_count":29,"area":null},{"id":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2307.09829","title":"What do neural networks learn in image classification? A frequency shortcut perspective","created":"2023-07-19","cited_by_count":28,"area":null},{"id":"2401.06654","title":"Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks","created":"2024-01-12","cited_by_count":28,"area":null},{"id":"2104.05107","title":"Towards a Collective Agenda on AI for Earth Science Data Analysis","created":"2021-04-11","cited_by_count":27,"area":null},{"id":"2303.00652","title":"Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science","created":"2023-03-01","cited_by_count":27,"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":"2104.01375","title":"Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensing","created":"2021-04-03","cited_by_count":26,"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":"2206.08871","title":"How Robust is Unsupervised Representation Learning to Distribution Shift?","created":"2022-06-17","cited_by_count":24,"area":null},{"id":"2408.08041","title":"The Clever Hans Effect in Unsupervised Learning","created":"2024-08-15","cited_by_count":24,"area":null},{"id":"2401.05821","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","created":"2024-01-11","cited_by_count":23,"area":"deeprl"},{"id":"2211.12486","title":"Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2311.16681","title":"Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations","created":"2023-11-28","cited_by_count":22,"area":null},{"id":"2305.06024","title":"A Survey on the Robustness of Computer Vision Models against Common Corruptions","created":"2023-05-10","cited_by_count":21,"area":null},{"id":"2308.09437","title":"From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space","created":"2023-08-18","cited_by_count":20,"area":"safety"},{"id":"2103.10005","title":"Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Dataset","created":"2021-03-18","cited_by_count":18,"area":null},{"id":"2108.10346","title":"Explaining Bayesian Neural Networks","created":"2021-08-23","cited_by_count":18,"area":null},{"id":"2111.07473","title":"Scrutinizing XAI using linear ground-truth data with suppressor variables","created":"2021-11-14","cited_by_count":18,"area":null},{"id":"2401.08527","title":"MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment","created":"2024-01-16","cited_by_count":18,"area":null},{"id":"2410.02331","title":"Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks","created":"2024-10-03","cited_by_count":18,"area":null},{"id":"2411.05561","title":"Objective drives the consistency of representational similarity across datasets","created":"2024-11-08","cited_by_count":18,"area":null},{"id":"2101.05186","title":"MC-LSTM: Mass-Conserving LSTM","created":"2021-01-13","cited_by_count":17,"area":null},{"id":"2102.13519","title":"PredDiff: Explanations and Interactions from Conditional Expectations","created":"2021-02-26","cited_by_count":17,"area":null},{"id":"2211.11426","title":"Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations","created":"2022-11-21","cited_by_count":17,"area":null},{"id":"2303.12641","title":"Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models","created":"2023-03-22","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":"2105.10172","title":"Explainable Machine Learning with Prior Knowledge: An Overview","created":"2021-05-21","cited_by_count":15,"area":null},{"id":"2107.04119","title":"Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction","created":"2021-07-01","cited_by_count":15,"area":null},{"id":"2305.17043","title":"Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2506.21521","title":"Potemkin Understanding in Large Language Models","created":"2025-06-26","cited_by_count":15,"area":null},{"id":"2206.04530","title":"DORA: Exploring Outlier Representations in Deep Neural Networks","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2310.01011","title":"Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation","created":"2023-10-02","cited_by_count":14,"area":"distill"},{"id":"2210.09404","title":"Measures of Information Reflect Memorization Patterns","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2211.13960","title":"The European AI Liability Directives -- Critique of a Half-Hearted Approach and Lessons for the Future","created":"2022-11-25","cited_by_count":12,"area":null},{"id":"2304.07007","title":"Dialogue Games for Benchmarking Language Understanding: Motivation, Taxonomy, Strategy","created":"2023-04-14","cited_by_count":12,"area":null},{"id":"2306.01464","title":"Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables","created":"2023-06-02","cited_by_count":12,"area":null},{"id":"2401.13796","title":"Don't Push the Button! Exploring Data Leakage Risks in Machine Learning and Transfer Learning","created":"2024-01-24","cited_by_count":12,"area":null},{"id":"2103.01259","title":"Uncertainty Quantification by Ensemble Learning for Computational Optical Form Measurements","created":"2021-03-01","cited_by_count":11,"area":null},{"id":"2105.07371","title":"Expressive Explanations of DNNs by Combining Concept Analysis with ILP","created":"2021-05-16","cited_by_count":11,"area":null},{"id":"2108.10949","title":"Robustness Evaluation of Entity Disambiguation Using Prior Probes:the Case of Entity Overshadowing","created":"2021-08-24","cited_by_count":11,"area":null},{"id":"2211.01738","title":"Analysis of a Deep Learning Model for 12-Lead ECG Classification Reveals Learned Features Similar to Diagnostic Criteria","created":"2022-11-03","cited_by_count":11,"area":null},{"id":"2212.13261","title":"Explainable AI for Bioinformatics: Methods, Tools, and Applications","created":"2022-12-25","cited_by_count":11,"area":null},{"id":"2307.10404","title":"Interpreting and Correcting Medical Image Classification with PIP-Net","created":"2023-07-19","cited_by_count":11,"area":null},{"id":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","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":"2105.04505","title":"Towards Benchmarking the Utility of Explanations for Model Debugging","created":"2021-05-10","cited_by_count":10,"area":null},{"id":"2203.06558","title":"AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation","created":"2022-03-13","cited_by_count":10,"area":null},{"id":"2204.13359","title":"Poly-CAM: High resolution class activation map for convolutional neural networks","created":"2022-04-28","cited_by_count":10,"area":null},{"id":"2307.14239","title":"Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI)","created":"2023-07-26","cited_by_count":10,"area":null},{"id":"2106.03016","title":"Topological Measurement of Deep Neural Networks Using Persistent Homology","created":"2021-06-06","cited_by_count":9,"area":null},{"id":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9,"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}],"next_cursor":"100"}