{"total":331,"rows":[{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2304.03738","title":"Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models","created":"2023-04-07","cited_by_count":148,"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":"2111.06420","title":"Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities","created":"2021-11-11","cited_by_count":125,"area":null},{"id":"2102.07817","title":"What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research","created":"2021-02-15","cited_by_count":119,"area":null},{"id":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113,"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":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"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":"2105.14944","title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","created":"2021-05-31","cited_by_count":88,"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":"2103.13084","title":"Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases","created":"2021-03-24","cited_by_count":77,"area":null},{"id":"2408.03943","title":"Building Machines that Learn and Think with People","created":"2024-07-22","cited_by_count":73,"area":null},{"id":"2304.05055","title":"A Comprehensive Survey on Deep Graph Representation Learning","created":"2023-04-11","cited_by_count":72,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","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":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55,"area":null},{"id":"2106.07875","title":"S-LIME: Stabilized-LIME for Model Explanation","created":"2021-06-15","cited_by_count":52,"area":null},{"id":"2107.11400","title":"Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks","created":"2021-07-23","cited_by_count":48,"area":null},{"id":"2211.00541","title":"Logic-Based Explainability in Machine Learning","created":"2022-10-24","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":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"area":null},{"id":"2101.01673","title":"Characterizing Intersectional Group Fairness with Worst-Case Comparisons","created":"2021-01-05","cited_by_count":42,"area":null},{"id":"2104.06172","title":"On the Computational Intelligibility of Boolean Classifiers","created":"2021-04-13","cited_by_count":40,"area":null},{"id":"2107.12045","title":"How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review","created":"2021-07-26","cited_by_count":39,"area":null},{"id":"2202.00787","title":"Achieving Fairness at No Utility Cost via Data Reweighing with Influence","created":"2022-02-01","cited_by_count":38,"area":null},{"id":"2209.11799","title":"Augmenting Interpretable Models with LLMs during Training","created":"2022-09-23","cited_by_count":38,"area":null},{"id":"2105.00108","title":"Explaining a Series of Models by Propagating Shapley Values","created":"2021-04-30","cited_by_count":37,"area":null},{"id":"2105.00290","title":"A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts","created":"2021-05-01","cited_by_count":33,"area":null},{"id":"2103.16886","title":"Neural Response Interpretation through the Lens of Critical Pathways","created":"2021-03-31","cited_by_count":32,"area":null},{"id":"2201.09051","title":"On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations","created":"2022-01-22","cited_by_count":32,"area":null},{"id":"2205.04766","title":"Explainable Deep Learning Methods in Medical Image Classification: A Survey","created":"2022-05-10","cited_by_count":32,"area":null},{"id":"2102.04201","title":"Reviewable Automated Decision-Making: A Framework for Accountable Algorithmic Systems","created":"2021-01-26","cited_by_count":31,"area":null},{"id":"2209.14279","title":"Causal Proxy Models for Concept-Based Model Explanations","created":"2022-09-28","cited_by_count":29,"area":null},{"id":"2101.01524","title":"\"Brilliant AI Doctor\" in Rural China: Tensions and Challenges in AI-Powered CDSS Deployment","created":"2021-01-04","cited_by_count":28,"area":null},{"id":"2106.00461","title":"To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods","created":"2021-06-01","cited_by_count":26,"area":null},{"id":"2109.00520","title":"The Role of Explainability in Assuring Safety of Machine Learning in Healthcare","created":"2021-09-01","cited_by_count":26,"area":null},{"id":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","cited_by_count":26,"area":null},{"id":"2401.13986","title":"Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning","created":"2024-01-25","cited_by_count":26,"area":null},{"id":"2102.04972","title":"Principles of Explanation in Human-AI Systems","created":"2021-02-09","cited_by_count":25,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2212.08507","title":"Robust Explanation Constraints for Neural Networks","created":"2022-12-16","cited_by_count":24,"area":null},{"id":"2107.03178","title":"Levels of explainable artificial intelligence for human-aligned conversational explanations","created":"2021-07-07","cited_by_count":21,"area":null},{"id":"2110.02932","title":"Machine Learning Practices Outside Big Tech: How Resource Constraints Challenge Responsible Development","created":"2021-10-06","cited_by_count":21,"area":null},{"id":"2206.10610","title":"Stop ordering machine learning algorithms by their explainability! A user-centered investigation of performance and explainability","created":"2022-06-20","cited_by_count":21,"area":null},{"id":"2109.01401","title":"CX-ToM: Counterfactual Explanations with Theory-of-Mind for Enhancing Human Trust in Image Recognition Models","created":"2021-09-03","cited_by_count":20,"area":null},{"id":"2203.13909","title":"Concept Embedding Analysis: A Review","created":"2022-03-25","cited_by_count":20,"area":null},{"id":"2208.10605","title":"SoK: Explainable Machine Learning for Computer Security Applications","created":"2022-08-22","cited_by_count":20,"area":null},{"id":"2211.15343","title":"Explainable Artificial Intelligence (XAI) from a user perspective- A synthesis of prior literature and problematizing avenues for future research","created":"2022-11-24","cited_by_count":20,"area":null},{"id":"2301.11970","title":"Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI","created":"2023-01-27","cited_by_count":20,"area":null},{"id":"2303.02794","title":"CoRTX: Contrastive Framework for Real-time Explanation","created":"2023-03-05","cited_by_count":20,"area":null},{"id":"2406.01317","title":"The Interpretable and Effective Graph Neural Additive Networks","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2406.12618","title":"From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP","created":"2024-06-18","cited_by_count":20,"area":null},{"id":"2101.09056","title":"A Few Good Counterfactuals: Generating Interpretable, Plausible and Diverse Counterfactual Explanations","created":"2021-01-22","cited_by_count":19,"area":null},{"id":"2103.08637","title":"Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition","created":"2021-03-15","cited_by_count":19,"area":null},{"id":"2109.03285","title":"Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud","created":"2021-09-07","cited_by_count":19,"area":null},{"id":"2402.04678","title":"FaithLM: Towards Faithful Explanations for Large Language Models","created":"2024-02-07","cited_by_count":19,"area":null},{"id":"2506.00085","title":"COSMIC: Generalized Refusal Direction Identification in LLM Activations","created":"2025-05-30","cited_by_count":19,"area":null},{"id":"2303.12806","title":"Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma","created":"2023-03-17","cited_by_count":18,"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":"2110.11952","title":"Optimal randomized classification trees","created":"2021-10-19","cited_by_count":16,"area":null},{"id":"2206.14724","title":"Private Graph Extraction via Feature Explanations","created":"2022-06-29","cited_by_count":16,"area":null},{"id":"2209.01874","title":"The Best Decisions Are Not the Best Advice: Making Adherence-Aware Recommendations","created":"2022-09-05","cited_by_count":16,"area":null},{"id":"2211.14736","title":"Attribution-based XAI Methods in Computer Vision: A Review","created":"2022-11-27","cited_by_count":16,"area":null},{"id":"2310.13007","title":"A Critical Survey on Fairness Benefits of Explainable AI","created":"2023-10-15","cited_by_count":16,"area":null},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2304.08861","title":"Impact Of Explainable AI On Cognitive Load: Insights From An Empirical Study","created":"2023-04-18","cited_by_count":15,"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":"2411.06090","title":"Concept Bottleneck Language Models For protein design","created":"2024-11-09","cited_by_count":15,"area":null},{"id":"2103.01096","title":"Counterfactual Explanations for Oblique Decision Trees: Exact, Efficient Algorithms","created":"2021-03-01","cited_by_count":14,"area":null},{"id":"2105.02626","title":"A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations","created":"2021-04-29","cited_by_count":14,"area":null},{"id":"2205.10032","title":"Survey on Fair Reinforcement Learning: Theory and Practice","created":"2022-05-20","cited_by_count":14,"area":null},{"id":"2107.08697","title":"DiCE4EL: Interpreting Process Predictions using a Milestone-Aware Counterfactual Approach","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2204.10716","title":"Hierarchical Label-wise Attention Transformer Model for Explainable ICD Coding","created":"2022-04-22","cited_by_count":13,"area":null},{"id":"2205.05306","title":"The Conflict Between Explainable and Accountable Decision-Making Algorithms","created":"2022-05-11","cited_by_count":13,"area":null},{"id":"2206.08529","title":"Accelerating Shapley Explanation via Contributive Cooperator Selection","created":"2022-06-17","cited_by_count":13,"area":null},{"id":"2210.09306","title":"Mitigating Covertly Unsafe Text within Natural Language Systems","created":"2022-10-17","cited_by_count":13,"area":null},{"id":"2210.11846","title":"Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2209.14974","title":"Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification","created":"2022-09-26","cited_by_count":12,"area":null},{"id":"2212.08733","title":"Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ","created":"2022-12-16","cited_by_count":12,"area":null},{"id":"2101.02647","title":"From Learning to Relearning: A Framework for Diminishing Bias in Social Robot Navigation","created":"2021-01-07","cited_by_count":11,"area":null},{"id":"2203.10794","title":"Human-Centric Artificial Intelligence Architecture for Industry 5.0 Applications","created":"2022-03-21","cited_by_count":11,"area":null},{"id":"2203.11547","title":"Explainability in reinforcement learning: perspective and position","created":"2022-03-22","cited_by_count":11,"area":null},{"id":"2211.17174","title":"Optimizing Explanations by Network Canonization and Hyperparameter Search","created":"2022-11-30","cited_by_count":11,"area":null},{"id":"2304.14864","title":"Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability","created":"2023-04-28","cited_by_count":11,"area":null},{"id":"2402.05160","title":"What's documented in AI? Systematic Analysis of 32K AI Model Cards","created":"2024-02-07","cited_by_count":11,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2405.16714","title":"Crafting Interpretable Embeddings by Asking LLMs Questions","created":"2024-05-26","cited_by_count":11,"area":null},{"id":"2103.08786","title":"Fairness and Transparency in Recommendation: The Users' Perspective","created":"2021-03-16","cited_by_count":10,"area":null},{"id":"2111.14651","title":"Multi-objective Explanations of GNN Predictions","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2207.03444","title":"Fairness and Bias in Robot Learning","created":"2022-07-07","cited_by_count":10,"area":null},{"id":"2211.05207","title":"Improving Clinician Performance in Classification of EEG Patterns on the Ictal-Interictal-Injury Continuum using Interpretable Machine Learning","created":"2022-11-09","cited_by_count":10,"area":null},{"id":"2302.10766","title":"Bridging the Transparency Gap: What Can Explainable AI Learn From the AI Act?","created":"2023-02-21","cited_by_count":10,"area":null},{"id":"2309.11960","title":"A Comprehensive Review on Financial Explainable AI","created":"2023-09-21","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":"2107.05911","title":"Model Transferability With Responsive Decision Subjects","created":"2021-07-13","cited_by_count":9,"area":null},{"id":"2204.12822","title":"A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directions","created":"2022-04-27","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":"2310.08565","title":"Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunities","created":"2023-10-12","cited_by_count":9,"area":null}],"next_cursor":"100"}