{"list":"other","total":54,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"1702.01135","title":"Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks","created":"2017-02-03","cited_by_count":744},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"1806.08049","title":"On the Robustness of Interpretability Methods","created":"2018-06-21","cited_by_count":314},{"id":"1904.07451","title":"Counterfactual Visual Explanations","created":"2019-04-16","cited_by_count":313},{"id":"1901.04592","title":"Interpretable machine learning: definitions, methods, and applications","created":"2019-01-14","cited_by_count":305},{"id":"1911.10500","title":"Causality for Machine Learning","created":"2019-11-24","cited_by_count":243},{"id":"1710.04806","title":"Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions","created":"2017-10-13","cited_by_count":234},{"id":"2011.07876","title":"A Survey on the Explainability of Supervised Machine Learning","created":"2020-11-16","cited_by_count":227},{"id":"1906.07983","title":"Explanations can be manipulated and geometry is to blame","created":"2019-06-19","cited_by_count":216},{"id":"1612.08468","title":"Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models","created":"2016-12-27","cited_by_count":213},{"id":"1708.08296","title":"Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models","created":"2017-08-28","cited_by_count":206},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178},{"id":"1905.10958","title":"Explainable Reinforcement Learning Through a Causal Lens","created":"2019-05-27","cited_by_count":177},{"id":"2008.05030","title":"Reliable Post hoc Explanations: Modeling Uncertainty in Explainability","created":"2020-08-11","cited_by_count":125},{"id":"2009.11698","title":"Principles and Practice of Explainable Machine Learning","created":"2020-09-18","cited_by_count":99},{"id":"1812.00891","title":"Interpretable Deep Learning under Fire","created":"2018-12-03","cited_by_count":74},{"id":"1906.10651","title":"Interpretable Image Recognition with Hierarchical Prototypes","created":"2019-06-25","cited_by_count":65},{"id":"2008.05803","title":"Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay","created":"2020-08-13","cited_by_count":57},{"id":"2105.10278","title":"On Explaining Random Forests with SAT","created":"2021-05-21","cited_by_count":57},{"id":"2105.03640","title":"On Guaranteed Optimal Robust Explanations for NLP Models","created":"2021-05-08","cited_by_count":54},{"id":"2010.11034","title":"On Explaining Decision Trees","created":"2020-10-21","cited_by_count":49},{"id":"1905.09957","title":"Robust Attribution Regularization","created":"2019-05-23","cited_by_count":47},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46},{"id":"2103.14651","title":"Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice","created":"2021-03-27","cited_by_count":45},{"id":"2012.10425","title":"Towards Robust Explanations for Deep Neural Networks","created":"2020-12-18","cited_by_count":43},{"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},{"id":"1910.02065","title":"Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods","created":"2019-10-04","cited_by_count":38},{"id":"2006.06643","title":"Smoothed Geometry for Robust Attribution","created":"2020-06-11","cited_by_count":38},{"id":"2210.08151","title":"ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model","created":"2022-10-15","cited_by_count":34},{"id":"2201.13169","title":"Causal Explanations and XAI","created":"2022-01-31","cited_by_count":30},{"id":"2212.01051","title":"VeriX: Towards Verified Explainability of Deep Neural Networks","created":"2022-12-02","cited_by_count":30},{"id":"2208.14878","title":"Formalising the Robustness of Counterfactual Explanations for Neural Networks","created":"2022-08-31","cited_by_count":24},{"id":"2212.08507","title":"Robust Explanation Constraints for Neural Networks","created":"2022-12-16","cited_by_count":24},{"id":"2107.01561","title":"Certifiably Robust Interpretation via Renyi Differential Privacy","created":"2021-07-04","cited_by_count":10},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10},{"id":"2410.14219","title":"Formal Explanations for Neuro-Symbolic AI","created":"2024-10-18","cited_by_count":6},{"id":"2409.03060","title":"Efficiently Computing Compact Formal Explanations","created":"2024-09-04","cited_by_count":4},{"id":"2208.00316","title":"On Interactive Explanations as Non-Monotonic Reasoning","created":"2022-07-30","cited_by_count":3},{"id":"2407.09127","title":"Robustness of Explainable Artificial Intelligence in Industrial Process Modelling","created":"2024-07-12","cited_by_count":2}],"next_cursor":null}