{"total":113,"rows":[{"id":"2209.07686","title":"Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango","created":"2022-09-16","cited_by_count":128,"area":"lr"},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2112.11313","title":"On the Adversarial Robustness of Causal Algorithmic Recourse","created":"2021-12-21","cited_by_count":56,"area":null},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55,"area":null},{"id":"2201.10295","title":"Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts","created":"2022-01-25","cited_by_count":53,"area":null},{"id":"2305.15853","title":"Sequential Integrated Gradients: a simple but effective method for explaining language models","created":"2023-05-25","cited_by_count":52,"area":null},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2312.14223","title":"Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation","created":"2023-12-21","cited_by_count":41,"area":null},{"id":"2203.06768","title":"Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse","created":"2022-03-13","cited_by_count":40,"area":null},{"id":"2111.00358","title":"A Survey on the Robustness of Feature Importance and Counterfactual Explanations","created":"2021-10-30","cited_by_count":39,"area":null},{"id":"2202.07728","title":"Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis","created":"2022-02-15","cited_by_count":38,"area":null},{"id":"2201.09051","title":"On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations","created":"2022-01-22","cited_by_count":32,"area":null},{"id":"2211.05427","title":"On the Privacy Risks of Algorithmic Recourse","created":"2022-11-10","cited_by_count":32,"area":"safety"},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2402.01928","title":"Robust Counterfactual Explanations in Machine Learning: A Survey","created":"2024-02-02","cited_by_count":29,"area":null},{"id":"2108.13025","title":"Transport-based Counterfactual Models","created":"2021-08-30","cited_by_count":27,"area":null},{"id":"2305.17021","title":"GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanations","created":"2023-05-26","cited_by_count":27,"area":null},{"id":"2208.14878","title":"Formalising the Robustness of Counterfactual Explanations for Neural Networks","created":"2022-08-31","cited_by_count":24,"area":null},{"id":"2208.14137","title":"On the Trade-Off between Actionable Explanations and the Right to be Forgotten","created":"2022-08-30","cited_by_count":20,"area":null},{"id":"2301.11113","title":"Finding Regions of Counterfactual Explanations via Robust Optimization","created":"2023-01-26","cited_by_count":19,"area":null},{"id":"2406.03193","title":"Graph Neural Network Explanations are Fragile","created":"2024-06-05","cited_by_count":19,"area":null},{"id":"2310.06668","title":"Latent Diffusion Counterfactual Explanations","created":"2023-10-10","cited_by_count":17,"area":"diffusion"},{"id":"2312.06564","title":"Promoting Counterfactual Robustness through Diversity","created":"2023-12-11","cited_by_count":17,"area":null},{"id":"2310.13007","title":"A Critical Survey on Fairness Benefits of Explainable AI","created":"2023-10-15","cited_by_count":16,"area":null},{"id":"2208.09967","title":"Inferring Sensitive Attributes from Model Explanations","created":"2022-08-21","cited_by_count":15,"area":null},{"id":"2304.08861","title":"Impact Of Explainable AI On Cognitive Load: Insights From An Empirical Study","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2112.06283","title":"Bayesian Persuasion for Algorithmic Recourse","created":"2021-12-12","cited_by_count":14,"area":null},{"id":"2307.05902","title":"Stability Guarantees for Feature Attributions with Multiplicative Smoothing","created":"2023-07-12","cited_by_count":14,"area":null},{"id":"2302.03465","title":"Robustness Implies Fairness in Causal Algorithmic Recourse","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2510.00047","title":"Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations","created":"2025-09-27","cited_by_count":12,"area":"mllm"},{"id":"2305.05840","title":"Achieving Diversity in Counterfactual Explanations: a Review and Discussion","created":"2023-05-10","cited_by_count":11,"area":null},{"id":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2111.01235","title":"Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions","created":"2021-11-01","cited_by_count":10,"area":null},{"id":"2411.10461","title":"Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scary","created":"2024-11-02","cited_by_count":10,"area":null},{"id":"2502.18156","title":"Can LLMs Explain Themselves Counterfactually?","created":"2025-02-25","cited_by_count":10,"area":null},{"id":"2204.06917","title":"Global Counterfactual Explanations: Investigations, Implementations and Improvements","created":"2022-04-14","cited_by_count":9,"area":null},{"id":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","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":"2302.14165","title":"GAM Coach: Towards Interactive and User-centered Algorithmic Recourse","created":"2023-02-27","cited_by_count":9,"area":null},{"id":"2303.09297","title":"Explaining Groups of Instances Counterfactually for XAI: A Use Case, Algorithm and User Study for Group-Counterfactuals","created":"2023-03-16","cited_by_count":9,"area":null},{"id":"2410.08007","title":"Time Can Invalidate Algorithmic Recourse","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2410.22598","title":"Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2306.13885","title":"Manipulation Risks in Explainable AI: The Implications of the Disagreement Problem","created":"2023-06-24","cited_by_count":7,"area":null},{"id":"2404.13736","title":"Interval Abstractions for Robust Counterfactual Explanations","created":"2024-04-21","cited_by_count":7,"area":null},{"id":"2210.06578","title":"FASTER-CE: Fast, Sparse, Transparent, and Robust Counterfactual Explanations","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2301.08833","title":"Bayesian Hierarchical Models for Counterfactual Estimation","created":"2023-01-21","cited_by_count":6,"area":null},{"id":"2305.17055","title":"Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2309.04676","title":"Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations","created":"2023-09-09","cited_by_count":6,"area":null},{"id":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2407.07482","title":"Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations","created":"2024-07-10","cited_by_count":6,"area":null},{"id":"2311.14137","title":"Privacy-Preserving Algorithmic Recourse","created":"2023-11-23","cited_by_count":5,"area":null},{"id":"2312.10648","title":"Faithful Model Explanations through Energy-Constrained Conformal Counterfactuals","created":"2023-12-17","cited_by_count":5,"area":null},{"id":"2403.01221","title":"A Two-Stage Algorithm for Cost-Efficient Multi-instance Counterfactual Explanations","created":"2024-03-02","cited_by_count":5,"area":null},{"id":"2404.18702","title":"Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots","created":"2024-04-29","cited_by_count":5,"area":null},{"id":"2601.20815","title":"GNN Explanations that do not Explain and How to find Them","created":"2026-01-28","cited_by_count":5,"area":null},{"id":"2601.23068","title":"ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2308.07198","title":"Explaining Black-Box Models through Counterfactuals","created":"2023-08-14","cited_by_count":4,"area":null},{"id":"2312.12477","title":"When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlook","created":"2023-12-19","cited_by_count":4,"area":null},{"id":"2312.16191","title":"SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning","created":"2023-12-22","cited_by_count":4,"area":null},{"id":"2410.01580","title":"Learning-Augmented Robust Algorithmic Recourse","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2202.11797","title":"Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four","created":"2022-02-23","cited_by_count":3,"area":null},{"id":"2309.04211","title":"Counterfactual Explanations via Locally-guided Sequential Algorithmic Recourse","created":"2023-09-08","cited_by_count":3,"area":null},{"id":"2402.08290","title":"The Effect of Data Poisoning on Counterfactual Explanations","created":"2024-02-13","cited_by_count":3,"area":"safety"},{"id":"2407.08497","title":"CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks (Technical Report)","created":"2024-07-11","cited_by_count":3,"area":null},{"id":"2410.22591","title":"FACEGroup: Feasible and Actionable Counterfactual Explanations for Group Fairness","created":"2024-10-29","cited_by_count":3,"area":null},{"id":"2501.05795","title":"Robust Counterfactual Explanations under Model Multiplicity Using Multi-Objective Optimization","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2509.21293","title":"Optimal Robust Recourse with $L^p$-Bounded Model Change","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2301.10407","title":"Don't Lie to Me: Avoiding Malicious Explanations with STEALTH","created":"2023-01-25","cited_by_count":2,"area":null},{"id":"2304.14606","title":"Algorithmic Recourse with Missing Values","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2307.12382","title":"CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models","created":"2023-07-23","cited_by_count":2,"area":"lr"},{"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":"2403.15603","title":"Forward Learning for Gradient-based Black-box Saliency Map Generation","created":"2024-03-22","cited_by_count":2,"area":null},{"id":"2404.16534","title":"SIDEs: Separating Idealization from Deceptive Explanations in xAI","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2410.02273","title":"Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recourse","created":"2024-10-03","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":"2502.03773","title":"ExpProof : Operationalizing Explanations for Confidential Models with ZKPs","created":"2025-02-06","cited_by_count":2,"area":null},{"id":"2505.00802","title":"Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Exploration","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2508.11441","title":"Informative Post-Hoc Explanations Only Exist for Simple Functions","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2601.20449","title":"Fair Recourse for All: Ensuring Individual and Group Fairness in Counterfactual Explanations","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2303.04579","title":"\"How to make them stay?\" -- Diverse Counterfactual Explanations of Employee Attrition","created":"2023-03-08","cited_by_count":1,"area":null},{"id":"2303.11111","title":"Iterative Partial Fulfillment of Counterfactual Explanations: Benefits and Risks","created":"2023-03-17","cited_by_count":1,"area":null},{"id":"2309.16146","title":"T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems","created":"2023-09-28","cited_by_count":1,"area":null},{"id":"2404.18736","title":"Mapping the Potential of Explainable AI for Fairness Along the AI Lifecycle","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2407.16010","title":"AIDE: Antithetical, Intent-based, and Diverse Example-Based Explanations","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2408.00166","title":"Review of Explainable Graph-Based Recommender Systems","created":"2024-07-31","cited_by_count":1,"area":null},{"id":"2410.14522","title":"Rethinking Distance Metrics for Counterfactual Explainability","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2410.15723","title":"S-CFE: Simple Counterfactual Explanations","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2503.23820","title":"When Counterfactual Reasoning Fails: Chaos and Real-World Complexity","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2505.02435","title":"A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2512.11433","title":"Back to the Baseline: Examining Baseline Effects on Explainability Metrics","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2602.10457","title":"Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generation","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2210.08902","title":"Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2306.04505","title":"Hardness of Deceptive Certificate Selection","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2309.16452","title":"On the Trade-offs between Adversarial Robustness and Actionable Explanations","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2311.00706","title":"Can AI Mitigate Human Perceptual Biases? A Pilot Study","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2402.15073","title":"Cost-Adaptive Recourse Recommendation by Adaptive Preference Elicitation","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2406.03012","title":"Towards Understanding the Influence of Training Samples on Explanations","created":"2024-06-05","cited_by_count":0,"area":null}],"next_cursor":"100"}