{"total":62,"rows":[{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190,"area":"distill"},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"id":"2106.01613","title":"NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning","created":"2021-06-03","cited_by_count":88,"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":"2101.08758","title":"How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations","created":"2021-01-21","cited_by_count":58,"area":null},{"id":"2202.01875","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":52,"area":null},{"id":"2107.13509","title":"The Who in XAI: How AI Background Shapes Perceptions of AI Explanations","created":"2021-07-28","cited_by_count":48,"area":null},{"id":"2402.02769","title":"Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2107.01614","title":"Survey: Leakage and Privacy at Inference Time","created":"2021-07-04","cited_by_count":44,"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":"2302.12881","title":"Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties","created":"2023-02-24","cited_by_count":24,"area":"diffusion"},{"id":"2206.03945","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","created":"2022-06-08","cited_by_count":20,"area":null},{"id":"2104.13299","title":"From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidence","created":"2021-04-27","cited_by_count":17,"area":null},{"id":"2203.02034","title":"Data-Efficient and Interpretable Tabular Anomaly Detection","created":"2022-03-03","cited_by_count":15,"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":"2403.09053","title":"Towards a theory of model distillation","created":"2024-03-14","cited_by_count":15,"area":null},{"id":"2306.00639","title":"Being Right for Whose Right Reasons?","created":"2023-06-01","cited_by_count":12,"area":null},{"id":"2210.02795","title":"Why Should I Choose You? AutoXAI: A Framework for Selecting and Tuning eXplainable AI Solutions","created":"2022-10-06","cited_by_count":10,"area":null},{"id":"2205.00706","title":"FedDKD: Federated Learning with Decentralized Knowledge Distillation","created":"2022-05-02","cited_by_count":9,"area":"distill"},{"id":"2209.15409","title":"Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2102.07444","title":"FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation","created":"2021-02-15","cited_by_count":6,"area":null},{"id":"2107.00296","title":"Explainable Diabetic Retinopathy Detection and Retinal Image Generation","created":"2021-07-01","cited_by_count":6,"area":null},{"id":"2202.08815","title":"GRAPHSHAP: Explaining Identity-Aware Graph Classifiers Through the Language of Motifs","created":"2022-02-17","cited_by_count":6,"area":null},{"id":"2401.14539","title":"Understanding Disparities in Post Hoc Machine Learning Explanation","created":"2024-01-25","cited_by_count":6,"area":null},{"id":"2406.07961","title":"Accurate Explanation Model for Image Classifiers using Class Association Embedding","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2505.04796","title":"Robust ML Auditing using Prior Knowledge","created":"2025-05-07","cited_by_count":6,"area":null},{"id":"2303.05500","title":"Users are the North Star for AI Transparency","created":"2023-03-09","cited_by_count":5,"area":null},{"id":"2104.11691","title":"Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities","created":"2021-04-22","cited_by_count":4,"area":null},{"id":"2301.07060","title":"Monotonicity for AI ethics and society: An empirical study of the monotonic neural additive model in criminology, education, health care, and finance","created":"2023-01-17","cited_by_count":4,"area":null},{"id":"2305.00799","title":"How to address monotonicity for model risk management?","created":"2023-04-28","cited_by_count":4,"area":null},{"id":"2105.06558","title":"Bias, Fairness, and Accountability with AI and ML Algorithms","created":"2021-05-13","cited_by_count":3,"area":null},{"id":"2201.06837","title":"Landslide Susceptibility Modeling by Interpretable Neural Network","created":"2022-01-18","cited_by_count":3,"area":null},{"id":"2209.03499","title":"Regulating eXplainable Artificial Intelligence (XAI) May Harm Consumers","created":"2022-09-07","cited_by_count":3,"area":null},{"id":"2211.12631","title":"A Generic Approach for Reproducible Model Distillation","created":"2022-11-22","cited_by_count":3,"area":null},{"id":"2310.15662","title":"Interactive Generalized Additive Model and Its Applications in Electric Load Forecasting","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2402.09947","title":"Explaining Probabilistic Models with Distributional Values","created":"2024-02-15","cited_by_count":3,"area":null},{"id":"2505.06907","title":"A Survey on Foundation Models for Personalized Federated Intelligence","created":"2025-05-11","cited_by_count":3,"area":null},{"id":"2505.18970","title":"Learning to Explain: Prototype-Based Surrogate Models for LLM Classification","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2306.12609","title":"Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities","created":"2023-06-22","cited_by_count":2,"area":null},{"id":"2311.03037","title":"Validity problems in clinical machine learning by indirect data labeling using consensus definitions","created":"2023-11-06","cited_by_count":2,"area":null},{"id":"2403.00315","title":"Axe the X in XAI: A Plea for Understandable AI","created":"2024-03-01","cited_by_count":2,"area":null},{"id":"2409.10338","title":"The 20 questions game to distinguish large language models","created":"2024-09-16","cited_by_count":2,"area":null},{"id":"2410.05675","title":"Understanding with toy surrogate models in machine learning","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2410.10535","title":"Transparent Networks for Multivariate Time Series","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2604.13332","title":"Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation Models","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2208.07211","title":"RuDi: Explaining Behavior Sequence Models by Automatic Statistics Generation and Rule Distillation","created":"2022-08-12","cited_by_count":1,"area":null},{"id":"2306.06473","title":"Interpretable Differencing of Machine Learning Models","created":"2023-06-10","cited_by_count":1,"area":null},{"id":"2409.03164","title":"RuleExplorer: A Scalable Matrix Visualization for Understanding Tree Ensemble Classifiers","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2101.08393","title":"Distilling Interpretable Models into Human-Readable Code","created":"2021-01-21","cited_by_count":0,"area":"distill"},{"id":"2106.12417","title":"False perfection in machine prediction: Detecting and assessing circularity problems in machine learning","created":"2021-06-23","cited_by_count":0,"area":null},{"id":"2110.15165","title":"Extracting Expert's Goals by What-if Interpretable Modeling","created":"2021-10-28","cited_by_count":0,"area":null},{"id":"2210.01848","title":"Explaining Patterns in Data with Language Models via Interpretable Autoprompting","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2211.15351","title":"Testing the effectiveness of saliency-based explainability in NLP using randomized survey-based experiments","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2306.07306","title":"Active Globally Explainable Learning for Medical Images via Class Association Embedding and Cyclic Adversarial Generation","created":"2023-06-12","cited_by_count":0,"area":null},{"id":"2406.08840","title":"Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2411.16895","title":"Explainable AI Approach using Near Misses Analysis","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2510.06125","title":"Downsized and Compromised?: Assessing the Faithfulness of Model Compression","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2602.16503","title":"Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2607.16357","title":"Reliable Remediation Impact Prediction for Black-Box Security Ratings","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.21839","title":"Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.08247","title":"zScore-N: A Neural Network for On-Chain Wallet Reputation Scoring","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.20058","title":"Evaluating Explanation Methods by the Predictors They Induce","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}