{"total":246,"rows":[{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638,"area":null},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"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":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"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":"2106.01613","title":"NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning","created":"2021-06-03","cited_by_count":88,"area":null},{"id":"2209.04012","title":"From Shapley Values to Generalized Additive Models and back","created":"2022-09-08","cited_by_count":60,"area":null},{"id":"2205.14120","title":"Neural Basis Models for Interpretability","created":"2022-05-27","cited_by_count":56,"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":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53,"area":null},{"id":"2210.06959","title":"A Survey on Explainable Anomaly Detection","created":"2022-10-13","cited_by_count":39,"area":null},{"id":"2410.02828","title":"PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System","created":"2024-10-01","cited_by_count":31,"area":"safety"},{"id":"2303.16047","title":"Exploring and Interacting with the Set of Good Sparse Generalized Additive Models","created":"2023-03-28","cited_by_count":30,"area":null},{"id":"2209.09326","title":"Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection","created":"2022-09-19","cited_by_count":28,"area":null},{"id":"2402.15350","title":"Farsight: Fostering Responsible AI Awareness During AI Application Prototyping","created":"2024-02-23","cited_by_count":28,"area":null},{"id":"2101.11948","title":"Choice modelling in the age of machine learning -- discussion paper","created":"2021-01-28","cited_by_count":26,"area":null},{"id":"2501.17546","title":"Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant","created":"2025-01-29","cited_by_count":26,"area":null},{"id":"2205.14108","title":"Scalable Interpretability via Polynomials","created":"2022-05-27","cited_by_count":25,"area":null},{"id":"2206.15465","title":"Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values","created":"2022-06-30","cited_by_count":25,"area":null},{"id":"2412.05152","title":"Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation","created":"2024-12-06","cited_by_count":25,"area":null},{"id":"2106.09680","title":"Accuracy, Interpretability, and Differential Privacy via Explainable Boosting","created":"2021-06-17","cited_by_count":24,"area":null},{"id":"2209.06528","title":"Explainable AI for clinical and remote health applications: a survey on tabular and time series data","created":"2022-09-14","cited_by_count":24,"area":null},{"id":"2108.07594","title":"Coalesced Multi-Output Tsetlin Machines with Clause Sharing","created":"2021-08-17","cited_by_count":22,"area":null},{"id":"2206.01612","title":"OmniXAI: A Library for Explainable AI","created":"2022-06-01","cited_by_count":21,"area":null},{"id":"2202.11389","title":"Fast Sparse Classification for Generalized Linear and Additive Models","created":"2022-02-23","cited_by_count":19,"area":null},{"id":"2206.02256","title":"Use-Case-Grounded Simulations for Explanation Evaluation","created":"2022-06-05","cited_by_count":19,"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":"2112.03245","title":"GAM Changer: Editing Generalized Additive Models with Interactive Visualization","created":"2021-12-06","cited_by_count":18,"area":null},{"id":"2301.11862","title":"Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean","created":"2023-01-27","cited_by_count":18,"area":null},{"id":"2104.08903","title":"SurvNAM: The machine learning survival model explanation","created":"2021-04-18","cited_by_count":16,"area":null},{"id":"2105.12837","title":"Fooling Partial Dependence via Data Poisoning","created":"2021-05-26","cited_by_count":16,"area":"safety"},{"id":"2305.16905","title":"Improving Neural Additive Models with Bayesian Principles","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2202.11043","title":"Differentially Private Estimation of Heterogeneous Causal Effects","created":"2022-02-22","cited_by_count":14,"area":null},{"id":"2302.06975","title":"A Review of the Role of Causality in Developing Trustworthy AI Systems","created":"2023-02-14","cited_by_count":14,"area":null},{"id":"2109.13770","title":"Micromodels for Efficient, Explainable, and Reusable Systems: A Case Study on Mental Health","created":"2021-09-28","cited_by_count":13,"area":null},{"id":"2110.08353","title":"Revisiting Popularity and Demographic Biases in Recommender Evaluation and Effectiveness","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2110.13369","title":"Partial Order in Chaos: Consensus on Feature Attributions in the Rashomon Set","created":"2021-10-26","cited_by_count":12,"area":null},{"id":"2205.04525","title":"Towards a multi-stakeholder value-based assessment framework for algorithmic systems","created":"2022-05-09","cited_by_count":12,"area":null},{"id":"2402.12518","title":"Gaussian Process Neural Additive Models","created":"2024-02-19","cited_by_count":11,"area":null},{"id":"2309.11960","title":"A Comprehensive Review on Financial Explainable AI","created":"2023-09-21","cited_by_count":10,"area":null},{"id":"2401.07871","title":"Explainable Predictive Maintenance: A Survey of Current Methods, Challenges and Opportunities","created":"2024-01-15","cited_by_count":10,"area":null},{"id":"2107.00219","title":"ControlBurn: Feature Selection by Sparse Forests","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2302.14165","title":"GAM Coach: Towards Interactive and User-centered Algorithmic Recourse","created":"2023-02-27","cited_by_count":9,"area":null},{"id":"2402.02933","title":"Intrinsic User-Centric Interpretability through Global Mixture of Experts","created":"2024-02-05","cited_by_count":9,"area":"moe"},{"id":"2103.03302","title":"Ensembles of Random SHAPs","created":"2021-03-04","cited_by_count":8,"area":null},{"id":"2510.10457","title":"Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data?","created":"2025-10-12","cited_by_count":8,"area":null},{"id":"2104.07874","title":"Translational NLP: A New Paradigm and General Principles for Natural Language Processing Research","created":"2021-04-16","cited_by_count":7,"area":null},{"id":"2105.14506","title":"Drop Clause: Enhancing Performance, Interpretability and Robustness of the Tsetlin Machine","created":"2021-05-30","cited_by_count":7,"area":null},{"id":"2107.09546","title":"Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions","created":"2021-07-20","cited_by_count":7,"area":null},{"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":"2211.01498","title":"On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2308.01157","title":"LLMs Understand Glass-Box Models, Discover Surprises, and Suggest Repairs","created":"2023-08-02","cited_by_count":7,"area":null},{"id":"2411.17207","title":"On the Efficiency of NLP-Inspired Methods for Tabular Deep Learning","created":"2024-11-26","cited_by_count":7,"area":null},{"id":"2512.08892","title":"Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders","created":"2025-12-09","cited_by_count":7,"area":"rag"},{"id":"2103.00370","title":"Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning","created":"2021-02-28","cited_by_count":6,"area":null},{"id":"2106.09111","title":"An Imprecise SHAP as a Tool for Explaining the Class Probability Distributions under Limited Training Data","created":"2021-06-16","cited_by_count":6,"area":null},{"id":"2202.11086","title":"StickyLand: Breaking the Linear Presentation of Computational Notebooks","created":"2022-02-22","cited_by_count":6,"area":null},{"id":"2204.09123","title":"GAM(e) changer or not? An evaluation of interpretable machine learning models based on additive model constraints","created":"2022-04-19","cited_by_count":6,"area":null},{"id":"2207.13770","title":"Calibrate: Interactive Analysis of Probabilistic Model Output","created":"2022-07-27","cited_by_count":6,"area":null},{"id":"2304.11749","title":"Missing Values and Imputation in Healthcare Data: Can Interpretable Machine Learning Help?","created":"2023-04-23","cited_by_count":6,"area":null},{"id":"2306.08853","title":"In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2307.08175","title":"Multi-Objective Optimization of Performance and Interpretability of Tabular Supervised Machine Learning Models","created":"2023-07-17","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":"2510.24815","title":"Tree Ensemble Explainability through the Hoeffding Functional Decomposition and TreeHFD Algorithm","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2105.13778","title":"\"Why Would I Trust Your Numbers?\" On the Explainability of Expected Values in Soccer","created":"2021-05-27","cited_by_count":5,"area":null},{"id":"2206.14384","title":"Framing Algorithmic Recourse for Anomaly Detection","created":"2022-06-29","cited_by_count":5,"area":null},{"id":"2303.15190","title":"Evaluating self-attention interpretability through human-grounded experimental protocol","created":"2023-03-27","cited_by_count":5,"area":null},{"id":"2403.14328","title":"Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression","created":"2024-03-21","cited_by_count":5,"area":"deeprl"},{"id":"2503.04261","title":"VirtualXAI: A User-Centric Framework for Explainability Assessment Leveraging GPT-Generated Personas","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2107.02661","title":"Does Dataset Complexity Matters for Model Explainers?","created":"2021-07-06","cited_by_count":4,"area":null},{"id":"2204.01689","title":"Using Explainable Boosting Machine to Compare Idiographic and Nomothetic Approaches for Ecological Momentary Assessment Data","created":"2022-04-04","cited_by_count":4,"area":null},{"id":"2205.07723","title":"Pest presence prediction using interpretable machine learning","created":"2022-05-16","cited_by_count":4,"area":null},{"id":"2208.05280","title":"TSInterpret: A unified framework for time series interpretability","created":"2022-08-10","cited_by_count":4,"area":null},{"id":"2305.04214","title":"PiML Toolbox for Interpretable Machine Learning Model Development and Diagnostics","created":"2023-05-07","cited_by_count":4,"area":null},{"id":"2306.02968","title":"Time Interpret: a Unified Model Interpretability Library for Time Series","created":"2023-06-05","cited_by_count":4,"area":null},{"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":"2402.01090","title":"Scalable Higher-Order Tensor Product Spline Models","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2410.23772","title":"Disentangling Interactions and Dependencies in Feature Attribution","created":"2024-10-31","cited_by_count":4,"area":null},{"id":"2604.16042","title":"Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures","created":"2026-04-17","cited_by_count":4,"area":"mechinterp"},{"id":"2104.06735","title":"Enabling Machine Learning Algorithms for Credit Scoring -- Explainable Artificial Intelligence (XAI) methods for clear understanding complex predictive models","created":"2021-04-14","cited_by_count":3,"area":null},{"id":"2107.05693","title":"Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff","created":"2021-07-12","cited_by_count":3,"area":null},{"id":"2108.04855","title":"Attention-like feature explanation for tabular data","created":"2021-08-10","cited_by_count":3,"area":null},{"id":"2108.11328","title":"Predicting Census Survey Response Rates With Parsimonious Additive Models and Structured Interactions","created":"2021-08-24","cited_by_count":3,"area":null},{"id":"2209.03805","title":"FAT Forensics: A Python Toolbox for Implementing and Deploying Fairness, Accountability and Transparency Algorithms in Predictive Systems","created":"2022-09-08","cited_by_count":3,"area":null},{"id":"2302.01985","title":"VR-LENS: Super Learning-based Cybersickness Detection and Explainable AI-Guided Deployment in Virtual Reality","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2302.08434","title":"On marginal feature attributions of tree-based models","created":"2023-02-16","cited_by_count":3,"area":null},{"id":"2305.03039","title":"SuperNOVA: Design Strategies and Opportunities for Interactive Visualization in Computational Notebooks","created":"2023-05-04","cited_by_count":3,"area":null},{"id":"2306.05120","title":"Explainable Predictive Maintenance","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2308.03730","title":"SurvBeX: An explanation method of the machine learning survival models based on the Beran estimator","created":"2023-08-07","cited_by_count":3,"area":null},{"id":"2308.07778","title":"An Interpretable Machine Learning Model with Deep Learning-based Imaging Biomarkers for Diagnosis of Alzheimer's Disease","created":"2023-08-15","cited_by_count":3,"area":null},{"id":"2308.14916","title":"RecRec: Algorithmic Recourse for Recommender Systems","created":"2023-08-28","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":"2402.16912","title":"An Adversarial Robustness Benchmark for Enterprise Network Intrusion Detection","created":"2024-02-25","cited_by_count":3,"area":null},{"id":"2404.04188","title":"Reliable Feature Selection for Adversarially Robust Cyber-Attack Detection","created":"2024-04-05","cited_by_count":3,"area":null},{"id":"2404.05908","title":"Interpretability in Symbolic Regression: a benchmark of Explanatory Methods using the Feynman data set","created":"2024-04-08","cited_by_count":3,"area":null},{"id":"2506.05586","title":"CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2107.14417","title":"Creating Powerful and Interpretable Models with Regression Networks","created":"2021-07-30","cited_by_count":2,"area":null},{"id":"2110.03513","title":"Accelerated Componentwise Gradient Boosting using Efficient Data Representation and Momentum-based Optimization","created":"2021-10-07","cited_by_count":2,"area":null}],"next_cursor":"100"}