{"total":219,"rows":[{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553,"area":null},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256,"area":null},{"id":"2201.12987","title":"Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism","created":"2022-01-31","cited_by_count":171,"area":null},{"id":"2202.01602","title":"The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":159,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2104.06643","title":"Generative Causal Explanations for Graph Neural Networks","created":"2021-04-14","cited_by_count":124,"area":null},{"id":"2302.02187","title":"Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations","created":"2023-02-04","cited_by_count":83,"area":null},{"id":"2106.05303","title":"Explaining Time Series Predictions with Dynamic Masks","created":"2021-06-09","cited_by_count":73,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2207.04154","title":"TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations","created":"2022-07-08","cited_by_count":66,"area":null},{"id":"2101.09824","title":"Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs","created":"2021-01-24","cited_by_count":64,"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":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2106.06804","title":"Entropy-based Logic Explanations of Neural Networks","created":"2021-06-12","cited_by_count":51,"area":null},{"id":"2310.05177","title":"Do Large Language Models Know about Facts?","created":"2023-10-08","cited_by_count":51,"area":null},{"id":"2311.00500","title":"Intriguing Properties of Data Attribution on Diffusion Models","created":"2023-11-01","cited_by_count":47,"area":"diffusion"},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2108.05149","title":"Logic Explained Networks","created":"2021-08-11","cited_by_count":45,"area":null},{"id":"2203.11279","title":"EEG based Emotion Recognition: A Tutorial and Review","created":"2022-03-16","cited_by_count":43,"area":null},{"id":"2103.02354","title":"Evaluating Robustness of Counterfactual Explanations","created":"2021-03-03","cited_by_count":41,"area":null},{"id":"2205.03295","title":"The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2205.07277","title":"Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations","created":"2022-05-15","cited_by_count":40,"area":null},{"id":"2106.01350","title":"On Efficiently Explaining Graph-Based Classifiers","created":"2021-06-02","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":"2306.02873","title":"DecompX: Explaining Transformers Decisions by Propagating Token Decomposition","created":"2023-06-05","cited_by_count":31,"area":null},{"id":"2108.04990","title":"Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing","created":"2021-08-11","cited_by_count":30,"area":null},{"id":"2212.11737","title":"The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations","created":"2022-12-22","cited_by_count":29,"area":null},{"id":"2204.06916","title":"Should I Follow AI-based Advice? Measuring Appropriate Reliance in Human-AI Decision-Making","created":"2022-04-14","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":"2109.01433","title":"Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process","created":"2021-09-03","cited_by_count":24,"area":null},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2303.05981","title":"Feature Importance: A Closer Look at Shapley Values and LOCO","created":"2023-03-10","cited_by_count":23,"area":null},{"id":"2410.18639","title":"Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models","created":"2024-10-24","cited_by_count":22,"area":"diffusion"},{"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":"2301.06676","title":"Explainable, Interpretable & Trustworthy AI for Intelligent Digital Twin: Case Study on Remaining Useful Life","created":"2023-01-17","cited_by_count":19,"area":null},{"id":"2101.07337","title":"Dissonance Between Human and Machine Understanding","created":"2021-01-18","cited_by_count":18,"area":null},{"id":"2312.14229","title":"Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2102.07048","title":"Connecting Interpretability and Robustness in Decision Trees through Separation","created":"2021-02-14","cited_by_count":16,"area":null},{"id":"2305.06754","title":"COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks","created":"2023-05-11","cited_by_count":16,"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":"2112.02625","title":"Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View","created":"2021-12-05","cited_by_count":15,"area":null},{"id":"2106.07410","title":"Model Explainability in Deep Learning Based Natural Language Processing","created":"2021-06-14","cited_by_count":14,"area":null},{"id":"2211.08943","title":"Comparing Explanation Methods for Traditional Machine Learning Models Part 1: An Overview of Current Methods and Quantifying Their Disagreement","created":"2022-11-16","cited_by_count":14,"area":null},{"id":"1802.02195","title":"Granger-causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks","created":"2018-02-06","cited_by_count":13,"area":"moe"},{"id":"2106.15355","title":"On the Interaction of Belief Bias and Explanations","created":"2021-06-29","cited_by_count":13,"area":null},{"id":"2107.11927","title":"On Blame Attribution for Accountable Multi-Agent Sequential Decision Making","created":"2021-07-26","cited_by_count":13,"area":null},{"id":"2111.10853","title":"Decorrelated Variable Importance","created":"2021-11-21","cited_by_count":13,"area":null},{"id":"2304.11218","title":"Explainability in AI Policies: A Critical Review of Communications, Reports, Regulations, and Standards in the EU, US, and UK","created":"2023-04-20","cited_by_count":13,"area":null},{"id":"2309.03234","title":"Natural Example-Based Explainability: a Survey","created":"2023-09-05","cited_by_count":13,"area":null},{"id":"2504.00573","title":"Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models","created":"2025-04-01","cited_by_count":13,"area":"rag"},{"id":"2202.12018","title":"Counterfactual Explanations for Predictive Business Process Monitoring","created":"2022-02-24","cited_by_count":12,"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":"2307.13463","title":"Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion","created":"2023-07-25","cited_by_count":12,"area":null},{"id":"2407.00219","title":"Evaluating Human Alignment and Model Faithfulness of LLM Rationale","created":"2024-06-28","cited_by_count":12,"area":null},{"id":"2403.11894","title":"From Explainable to Interpretable Deep Learning for Natural Language Processing in Healthcare: How Far from Reality?","created":"2024-03-18","cited_by_count":11,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2103.00752","title":"Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence","created":"2021-03-01","cited_by_count":10,"area":null},{"id":"2104.04075","title":"Towards a Rigorous Evaluation of Explainability for Multivariate Time Series","created":"2021-04-06","cited_by_count":10,"area":null},{"id":"2201.11701","title":"Model Agnostic Interpretability for Multiple Instance Learning","created":"2022-01-27","cited_by_count":10,"area":null},{"id":"2401.16407","title":"Is K-fold cross validation the best model selection method for Machine Learning?","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2110.03184","title":"Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2110.07120","title":"Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2211.14858","title":"\"Explain it in the Same Way!\" -- Model-Agnostic Group Fairness of Counterfactual Explanations","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2310.13664","title":"Explainable Depression Symptom Detection in Social Media","created":"2023-10-20","cited_by_count":9,"area":null},{"id":"2403.03322","title":"Deep Configuration Performance Learning: A Systematic Survey and Taxonomy","created":"2024-03-05","cited_by_count":8,"area":null},{"id":"2410.08007","title":"Time Can Invalidate Algorithmic Recourse","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2411.19858","title":"What fifty-one years of Linguistics and Artificial Intelligence research tell us about their correlation: A scientometric analysis","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2210.04371","title":"A Detailed Study of Interpretability of Deep Neural Network based Top Taggers","created":"2022-10-09","cited_by_count":7,"area":null},{"id":"2304.14094","title":"Categorical Foundations of Explainable AI: A Unifying Theory","created":"2023-04-27","cited_by_count":7,"area":null},{"id":"2104.04144","title":"Individual Explanations in Machine Learning Models: A Survey for Practitioners","created":"2021-04-09","cited_by_count":6,"area":null},{"id":"2109.03756","title":"Diagnostics-Guided Explanation Generation","created":"2021-09-08","cited_by_count":6,"area":null},{"id":"2209.00445","title":"Interpreting Embedding Spaces by Conceptualization","created":"2022-08-22","cited_by_count":6,"area":null},{"id":"2210.08500","title":"This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text","created":"2022-10-16","cited_by_count":6,"area":null},{"id":"2301.04020","title":"Quant 4.0: Engineering Quantitative Investment with Automated, Explainable and Knowledge-driven Artificial Intelligence","created":"2022-12-13","cited_by_count":6,"area":null},{"id":"2310.14817","title":"Text2Topic: Multi-Label Text Classification System for Efficient Topic Detection in User Generated Content with Zero-Shot Capabilities","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2310.15472","title":"Interpretable Survival Analysis for Heart Failure Risk Prediction","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2106.00839","title":"Algorithmic Insurance","created":"2021-06-01","cited_by_count":5,"area":null},{"id":"2107.06580","title":"IFedAvg: Interpretable Data-Interoperability for Federated Learning","created":"2021-07-14","cited_by_count":5,"area":null},{"id":"2107.08045","title":"Desiderata for Explainable AI in statistical production systems of the European Central Bank","created":"2021-07-18","cited_by_count":5,"area":null},{"id":"2108.04035","title":"Mixture of Linear Models Co-supervised by Deep Neural Networks","created":"2021-08-05","cited_by_count":5,"area":null},{"id":"2112.04698","title":"Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges","created":"2021-12-09","cited_by_count":5,"area":null},{"id":"2112.06858","title":"Why Are You Weird? Infusing Interpretability in Isolation Forest for Anomaly Detection","created":"2021-12-13","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":"2312.13616","title":"Navigating the Structured What-If Spaces: Counterfactual Generation via Structured Diffusion","created":"2023-12-21","cited_by_count":5,"area":"diffusion"},{"id":"2406.00539","title":"CONFINE: Conformal Prediction for Interpretable Neural Networks","created":"2024-06-01","cited_by_count":5,"area":null},{"id":"2406.17931","title":"CAT: Interpretable Concept-based Taylor Additive Models","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2407.19683","title":"Revisiting the robustness of post-hoc interpretability methods","created":"2024-07-29","cited_by_count":5,"area":null},{"id":"2408.06502","title":"Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers","created":"2024-08-12","cited_by_count":5,"area":null},{"id":"2102.09687","title":"SQAPlanner: Generating Data-Informed Software Quality Improvement Plans","created":"2021-02-19","cited_by_count":4,"area":null},{"id":"2105.10400","title":"Word-level Text Highlighting of Medical Texts for Telehealth Services","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2202.12678","title":"Deep Learning, Natural Language Processing, and Explainable Artificial Intelligence in the Biomedical Domain","created":"2022-02-25","cited_by_count":4,"area":null},{"id":"2205.05661","title":"How Platform-User Power Relations Shape Algorithmic Accountability: A Case Study of Instant Loan Platforms and Financially Stressed Users in India","created":"2022-05-11","cited_by_count":4,"area":null},{"id":"2209.07623","title":"Studying the explanations for the automated prediction of bug and non-bug issues using LIME and SHAP","created":"2022-09-15","cited_by_count":4,"area":null},{"id":"2211.04476","title":"Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing","created":"2022-11-08","cited_by_count":4,"area":null},{"id":"2212.09848","title":"(Psycho-)Linguistic Features Meet Transformer Models for Improved Explainable and Controllable Text Simplification","created":"2022-12-19","cited_by_count":4,"area":null},{"id":"2305.07663","title":"Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces","created":"2023-04-30","cited_by_count":4,"area":null},{"id":"2308.11975","title":"Approximating Score-based Explanation Techniques Using Conformal Regression","created":"2023-08-23","cited_by_count":4,"area":null},{"id":"2310.08071","title":"Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2310.11340","title":"Contextualized Machine Learning","created":"2023-10-17","cited_by_count":4,"area":null},{"id":"2311.00393","title":"Augmenting deep neural networks with symbolic knowledge: Towards trustworthy and interpretable AI for education","created":"2023-11-01","cited_by_count":4,"area":null}],"next_cursor":"100"}