{"total":142,"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":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249,"area":null},{"id":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178,"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":"2103.02023","title":"EnD: Entangling and Disentangling deep representations for bias correction","created":"2021-03-02","cited_by_count":105,"area":null},{"id":"2202.00449","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","created":"2022-02-01","cited_by_count":102,"area":null},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91,"area":null},{"id":"2103.12308","title":"IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography","created":"2021-03-23","cited_by_count":72,"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":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53,"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":"2106.03922","title":"Interactive Label Cleaning with Example-based Explanations","created":"2021-06-07","cited_by_count":49,"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":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2301.11333","title":"Knowing About Knowing: An Illusion of Human Competence Can Hinder Appropriate Reliance on AI Systems","created":"2023-01-25","cited_by_count":41,"area":null},{"id":"2405.18842","title":"Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset","created":"2024-05-29","cited_by_count":38,"area":"mllm"},{"id":"2112.03753","title":"Tell me why! Explanations support learning relational and causal structure","created":"2021-12-07","cited_by_count":36,"area":null},{"id":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"area":null},{"id":"2111.07668","title":"Fast Axiomatic Attribution for Neural Networks","created":"2021-11-15","cited_by_count":35,"area":null},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"area":null},{"id":"2308.13453","title":"Learning to Intervene on Concept Bottlenecks","created":"2023-08-25","cited_by_count":29,"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":"2306.15786","title":"An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning","created":"2023-06-27","cited_by_count":25,"area":null},{"id":"2106.13876","title":"Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations","created":"2021-06-25","cited_by_count":24,"area":null},{"id":"2112.02290","title":"Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations","created":"2021-12-04","cited_by_count":24,"area":null},{"id":"2303.07811","title":"ICICLE: Interpretable Class Incremental Continual Learning","created":"2023-03-14","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":"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":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"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":"2402.08280","title":"Pix2Code: Learning to Compose Neural Visual Concepts as Programs","created":"2024-02-13","cited_by_count":18,"area":null},{"id":"2405.14956","title":"Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning","created":"2024-05-23","cited_by_count":18,"area":"deeprl"},{"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":"2309.08395","title":"Learning by Self-Explaining","created":"2023-09-15","cited_by_count":17,"area":null},{"id":"2303.11932","title":"Studying How to Efficiently and Effectively Guide Models with Explanations","created":"2023-03-21","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":"2111.03740","title":"Toward Learning Human-aligned Cross-domain Robust Models by Countering Misaligned Features","created":"2021-11-05","cited_by_count":14,"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":"2402.00491","title":"EXMOS: Explanatory Model Steering Through Multifaceted Explanations and Data Configurations","created":"2024-02-01","cited_by_count":14,"area":null},{"id":"2406.09949","title":"Neural Concept Binder","created":"2024-06-14","cited_by_count":14,"area":"lr"},{"id":"2210.07024","title":"Self-explaining deep models with logic rule reasoning","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2406.03997","title":"HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning","created":"2024-06-06","cited_by_count":11,"area":"deeprl"},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","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":"2211.08285","title":"Identifying Spurious Correlations and Correcting them with an Explanation-based Learning","created":"2022-11-15","cited_by_count":10,"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":"2407.04370","title":"Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density","created":"2024-07-05","cited_by_count":10,"area":null},{"id":"2103.15429","title":"Efficient Explanations from Empirical Explainers","created":"2021-03-29","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},{"id":"2210.10332","title":"Revision Transformers: Instructing Language Models to Change their Values","created":"2022-10-19","cited_by_count":8,"area":null},{"id":"2306.07743","title":"V-LoL: A Diagnostic Dataset for Visual Logical Learning","created":"2023-06-13","cited_by_count":8,"area":"lr"},{"id":"2401.03002","title":"Prompt-driven Latent Domain Generalization for Medical Image Classification","created":"2024-01-05","cited_by_count":8,"area":null},{"id":"2402.06434","title":"Where is the Truth? The Risk of Getting Confounded in a Continual World","created":"2024-02-09","cited_by_count":8,"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":"2409.12809","title":"Don't be Fooled: The Misinformation Effect of Explanations in Human-AI Collaboration","created":"2024-09-19","cited_by_count":8,"area":null},{"id":"2203.03668","title":"A Typology for Exploring the Mitigation of Shortcut Behavior","created":"2022-03-04","cited_by_count":7,"area":null},{"id":"2209.12476","title":"Impact of Feedback Type on Explanatory Interactive Learning","created":"2022-09-26","cited_by_count":7,"area":null},{"id":"2306.05801","title":"Strategies to exploit XAI to improve classification systems","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2402.12921","title":"Right on Time: Revising Time Series Models by Constraining their Explanations","created":"2024-02-20","cited_by_count":7,"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":"2409.14377","title":"To Err Is AI! Debugging as an Intervention to Facilitate Appropriate Reliance on AI Systems","created":"2024-09-22","cited_by_count":7,"area":null},{"id":"2510.17524","title":"Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples","created":"2025-10-20","cited_by_count":7,"area":"distill"},{"id":"2511.18964","title":"Synthesizing Visual Concepts as Vision-Language Programs","created":"2025-11-24","cited_by_count":6,"area":"lr"},{"id":"2201.03131","title":"Systematic biases when using deep neural networks for annotating large catalogs of astronomical images","created":"2022-01-10","cited_by_count":5,"area":null},{"id":"2203.15071","title":"User Driven Model Adjustment via Boolean Rule Explanations","created":"2022-03-28","cited_by_count":5,"area":null},{"id":"2204.02661","title":"CAIPI in Practice: Towards Explainable Interactive Medical Image Classification","created":"2022-04-06","cited_by_count":5,"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":"2312.03437","title":"Data-Centric Digital Agriculture: A Perspective","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2404.09601","title":"Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression","created":"2024-04-15","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":"2501.01441","title":"Explanatory Debiasing: Involving Domain Experts in the Data Generation Process to Mitigate Representation Bias in AI Systems","created":"2024-12-26","cited_by_count":5,"area":null},{"id":"2103.14874","title":"Human-in-the-loop Handling of Knowledge Drift","created":"2021-03-27","cited_by_count":4,"area":null},{"id":"2109.11160","title":"Toward a Unified Framework for Debugging Concept-based Models","created":"2021-09-23","cited_by_count":4,"area":null},{"id":"2110.02058","title":"Interactively Providing Explanations for Transformer Language Models","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2310.02063","title":"Lessons Learned from EXMOS User Studies: A Technical Report Summarizing Key Takeaways from User Studies Conducted to Evaluate The EXMOS Platform","created":"2023-10-03","cited_by_count":4,"area":null},{"id":"2310.05442","title":"Establishing Trustworthiness: Rethinking Tasks and Model Evaluation","created":"2023-10-09","cited_by_count":4,"area":"lr"},{"id":"2310.07882","title":"The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2403.07078","title":"Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning","created":"2024-03-11","cited_by_count":4,"area":null},{"id":"2403.16501","title":"Learning To Guide Human Decision Makers With Vision-Language Models","created":"2024-03-25","cited_by_count":4,"area":null},{"id":"2405.13038","title":"An Explanatory Model Steering System for Collaboration between Domain Experts and AI","created":"2024-05-17","cited_by_count":4,"area":null},{"id":"2104.10553","title":"Rethinking Annotation Granularity for Overcoming Shortcuts in Deep Learning-based Radiograph Diagnosis: A Multicenter Study","created":"2021-04-21","cited_by_count":3,"area":null},{"id":"2304.08094","title":"Trust and Transparency in Recommender Systems","created":"2023-04-17","cited_by_count":3,"area":null},{"id":"2304.13836","title":"On Pitfalls of $\\textit{RemOve-And-Retrain}$: Data Processing Inequality Perspective","created":"2023-04-26","cited_by_count":3,"area":null},{"id":"2305.15149","title":"Reliability Scores from Saliency Map Clusters for Improved Image-based Harvest-Readiness Prediction in Cauliflower","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2311.04813","title":"Be Careful When Evaluating Explanations Regarding Ground Truth","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2311.12813","title":"Targeted Activation Penalties Help CNNs Ignore Spurious Signals","created":"2023-09-22","cited_by_count":3,"area":null},{"id":"2407.20067","title":"xAI-Drop: Don't Use What You Cannot Explain","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2504.07257","title":"Better Decisions through the Right Causal World Model","created":"2025-04-09","cited_by_count":3,"area":"wm"},{"id":"2506.05533","title":"Personalized Interpretability -- Interactive Alignment of Prototypical Parts Networks","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2506.13727","title":"Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs","created":"2025-06-16","cited_by_count":3,"area":"mechinterp"},{"id":"2202.00391","title":"Right for the Right Latent Factors: Debiasing Generative Models via Disentanglement","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2202.08566","title":"Efficient and Reliable Probabilistic Interactive Learning with Structured Outputs","created":"2022-02-17","cited_by_count":2,"area":null},{"id":"2204.12941","title":"Unsupervised Learning of Unbiased Visual Representations","created":"2022-04-26","cited_by_count":2,"area":null},{"id":"2303.06419","title":"Use Perturbations when Learning from Explanations","created":"2023-03-11","cited_by_count":2,"area":null},{"id":"2304.07136","title":"One Explanation Does Not Fit XIL","created":"2023-04-14","cited_by_count":2,"area":null},{"id":"2305.11755","title":"Visualization for Recommendation Explainability: A Survey and New Perspectives","created":"2023-05-19","cited_by_count":2,"area":null}],"next_cursor":"100"}