{"list":"other","total":66,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1711.00399","title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR","created":"2017-11-01","cited_by_count":1089},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"1806.00069","title":"Explaining Explanations: An Overview of Interpretability of Machine Learning","created":"2018-05-31","cited_by_count":508},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"1907.07374","title":"A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI","created":"2019-07-17","cited_by_count":404},{"id":"1706.07979","title":"Methods for Interpreting and Understanding Deep Neural Networks","created":"2017-06-24","cited_by_count":345},{"id":"1506.06579","title":"Understanding Neural Networks Through Deep Visualization","created":"2015-06-22","cited_by_count":334},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"1901.09392","title":"On the (In)fidelity and Sensitivity for Explanations","created":"2019-01-27","cited_by_count":310},{"id":"1901.04592","title":"Interpretable machine learning: definitions, methods, and applications","created":"2019-01-14","cited_by_count":305},{"id":"1812.04608","title":"Metrics for Explainable AI: Challenges and Prospects","created":"2018-12-11","cited_by_count":260},{"id":"2002.06278","title":"Algorithmic Recourse: from Counterfactual Explanations to Interventions","created":"2020-02-14","cited_by_count":250},{"id":"1808.00033","title":"Techniques for Interpretable Machine Learning","created":"2018-07-31","cited_by_count":238},{"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":"2103.02582","title":"D'ya like DAGs? A Survey on Structure Learning and Causal Discovery","created":"2021-03-03","cited_by_count":211},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205},{"id":"1910.13413","title":"Feature relevance quantification in explainable AI: A causal problem","created":"2019-10-29","cited_by_count":167},{"id":"1901.10912","title":"A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms","created":"2019-01-30","cited_by_count":158},{"id":"2006.06831","title":"Algorithmic recourse under imperfect causal knowledge: a probabilistic approach","created":"2020-06-11","cited_by_count":140},{"id":"1811.01439","title":"Explaining Explanations in AI","created":"2018-11-04","cited_by_count":137},{"id":"1907.07165","title":"Explaining Classifiers with Causal Concept Effect (CaCE)","created":"2019-07-16","cited_by_count":135},{"id":"1912.01451","title":"Sanity Checks for Saliency Metrics","created":"2019-11-29","cited_by_count":119},{"id":"1707.00819","title":"Causal Consistency of Structural Equation Models","created":"2017-07-04","cited_by_count":118},{"id":"1902.02041","title":"Fooling Neural Network Interpretations via Adversarial Model Manipulation","created":"2019-02-06","cited_by_count":112},{"id":"1812.03789","title":"Abstracting Causal Models","created":"2018-12-10","cited_by_count":107},{"id":"2002.04138","title":"Explaining Explanations: Axiomatic Feature Interactions for Deep Networks","created":"2020-02-10","cited_by_count":103},{"id":"1907.09294","title":"The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations","created":"2019-07-22","cited_by_count":97},{"id":"1902.02302","title":"Neural Network Attributions: A Causal Perspective","created":"2019-02-06","cited_by_count":77},{"id":"1503.01161","title":"The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification","created":"2015-03-03","cited_by_count":76},{"id":"2010.12265","title":"Model Interpretability through the Lens of Computational Complexity","created":"2020-10-23","cited_by_count":75},{"id":"2010.06529","title":"On the Fairness of Causal Algorithmic Recourse","created":"2020-10-13","cited_by_count":70},{"id":"2305.19951","title":"Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts","created":"2023-05-31","cited_by_count":63},{"id":"2103.04244","title":"Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications","created":"2021-03-07","cited_by_count":59},{"id":"2012.01805","title":"Interpretability and Explainability: A Machine Learning Zoo Mini-tour","created":"2020-12-03","cited_by_count":55},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53},{"id":"1810.00184","title":"Stakeholders in Explainable AI","created":"2018-09-29","cited_by_count":48},{"id":"1806.07498","title":"Defining Locality for Surrogates in Post-hoc Interpretablity","created":"2018-06-19","cited_by_count":33},{"id":"2201.13169","title":"Causal Explanations and XAI","created":"2022-01-31","cited_by_count":30},{"id":"2406.02981","title":"Local vs. Global Interpretability: A Computational Complexity Perspective","created":"2024-06-05","cited_by_count":23},{"id":"2309.07742","title":"Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning","created":"2023-09-14","cited_by_count":22},{"id":"2309.09901","title":"The role of causality in explainable artificial intelligence","created":"2023-09-18","cited_by_count":17},{"id":"2410.08025","title":"The Computational Complexity of Circuit Discovery for Inner Interpretability","created":"2024-10-10","cited_by_count":15},{"id":"2212.06925","title":"On the Relationship Between Explanation and Prediction: A Causal View","created":"2022-12-13","cited_by_count":14},{"id":"2407.18755","title":"Score matching through the roof: linear, nonlinear, and latent variables causal discovery","created":"2024-07-26","cited_by_count":10},{"id":"1910.05664","title":"Extracting Incentives from Black-Box Decisions","created":"2019-10-13","cited_by_count":8},{"id":"2205.15406","title":"From Explanation to Recommendation: Ethical Standards for Algorithmic Recourse","created":"2022-05-30","cited_by_count":6},{"id":"2211.06499","title":"Social Construction of XAI: Do We Need One Definition to Rule Them All?","created":"2022-11-11","cited_by_count":6},{"id":"2412.05592","title":"From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation","created":"2024-12-07","cited_by_count":4},{"id":"2209.03450","title":"Seeking Interpretability and Explainability in Binary Activated Neural Networks","created":"2022-09-07","cited_by_count":3},{"id":"2408.10085","title":"MASALA: Model-Agnostic Surrogate Explanations by Locality Adaptation","created":"2024-08-19","cited_by_count":2},{"id":"2410.20161","title":"Causal Abstraction in Model Interpretability: A Compact Survey","created":"2024-10-26","cited_by_count":2}],"next_cursor":null}