{"total":1206,"rows":[{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940,"area":"lr"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250,"area":null},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152,"area":null},{"id":"2304.08295","title":"Interactive and Explainable Region-guided Radiology Report Generation","created":"2023-04-17","cited_by_count":140,"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":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2111.06420","title":"Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities","created":"2021-11-11","cited_by_count":125,"area":null},{"id":"2310.19775","title":"Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions","created":"2023-10-30","cited_by_count":125,"area":null},{"id":"2101.04719","title":"Expanding Explainability: Towards Social Transparency in AI systems","created":"2021-01-12","cited_by_count":124,"area":null},{"id":"2110.10790","title":"Human-Centered Explainable AI (XAI): From Algorithms to User Experiences","created":"2021-10-20","cited_by_count":123,"area":null},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"area":null},{"id":"2102.03322","title":"CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks","created":"2021-02-05","cited_by_count":119,"area":null},{"id":"2102.07817","title":"What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research","created":"2021-02-15","cited_by_count":119,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2204.08570","title":"A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability","created":"2022-04-18","cited_by_count":118,"area":null},{"id":"2212.06823","title":"Explanations Can Reduce Overreliance on AI Systems During Decision-Making","created":"2022-12-13","cited_by_count":111,"area":null},{"id":"2305.18029","title":"Faithfulness Tests for Natural Language Explanations","created":"2023-05-29","cited_by_count":107,"area":null},{"id":"2401.06730","title":"Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty","created":"2024-01-12","cited_by_count":106,"area":null},{"id":"2306.01574","title":"Probabilistic Concept Bottleneck Models","created":"2023-06-02","cited_by_count":101,"area":null},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101,"area":null},{"id":"2210.11841","title":"Diffusion Visual Counterfactual Explanations","created":"2022-10-21","cited_by_count":96,"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":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"area":null},{"id":"2210.11584","title":"Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations","created":"2022-10-20","cited_by_count":85,"area":null},{"id":"2103.01035","title":"If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques","created":"2021-02-26","cited_by_count":82,"area":null},{"id":"2103.05154","title":"Explanations in Autonomous Driving: A Survey","created":"2021-03-09","cited_by_count":81,"area":null},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79,"area":null},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2103.10663","title":"XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations","created":"2021-03-19","cited_by_count":73,"area":null},{"id":"2112.11561","title":"Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions","created":"2021-12-21","cited_by_count":73,"area":"driving"},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73,"area":null},{"id":"2301.07255","title":"Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations","created":"2023-01-18","cited_by_count":73,"area":null},{"id":"2408.03943","title":"Building Machines that Learn and Think with People","created":"2024-07-22","cited_by_count":73,"area":null},{"id":"2105.11266","title":"Argumentative XAI: A Survey","created":"2021-05-24","cited_by_count":67,"area":null},{"id":"2302.12389","title":"Explainable AI is Dead, Long Live Explainable AI! Hypothesis-driven decision support","created":"2023-02-24","cited_by_count":66,"area":null},{"id":"2101.09824","title":"Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs","created":"2021-01-24","cited_by_count":64,"area":null},{"id":"2104.10482","title":"GraphSVX: Shapley Value Explanations for Graph Neural Networks","created":"2021-04-18","cited_by_count":64,"area":null},{"id":"2210.03735","title":"\"Help Me Help the AI\": Understanding How Explainability Can Support Human-AI Interaction","created":"2022-10-02","cited_by_count":63,"area":null},{"id":"2104.07411","title":"NICE: An Algorithm for Nearest Instance Counterfactual Explanations","created":"2021-04-15","cited_by_count":62,"area":null},{"id":"2103.04244","title":"Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications","created":"2021-03-07","cited_by_count":59,"area":null},{"id":"2105.06965","title":"Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction","created":"2021-05-14","cited_by_count":59,"area":null},{"id":"2101.05303","title":"Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making","created":"2021-01-13","cited_by_count":58,"area":null},{"id":"2105.10278","title":"On Explaining Random Forests with SAT","created":"2021-05-21","cited_by_count":57,"area":null},{"id":"2103.11972","title":"Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals","created":"2021-03-22","cited_by_count":55,"area":null},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53,"area":null},{"id":"2202.05402","title":"Do People Engage Cognitively with AI? Impact of AI Assistance on Incidental Learning","created":"2022-02-11","cited_by_count":53,"area":null},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53,"area":null},{"id":"2402.10086","title":"Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2310.12558","title":"Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong","created":"2023-10-19","cited_by_count":51,"area":null},{"id":"2305.07722","title":"In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making","created":"2023-05-12","cited_by_count":50,"area":null},{"id":"2104.12669","title":"Exploiting Explanations for Model Inversion Attacks","created":"2021-04-26","cited_by_count":49,"area":null},{"id":"2106.03922","title":"Interactive Label Cleaning with Example-based Explanations","created":"2021-06-07","cited_by_count":49,"area":null},{"id":"2101.07685","title":"GLocalX -- From Local to Global Explanations of Black Box AI Models","created":"2021-01-19","cited_by_count":48,"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":"2211.00541","title":"Logic-Based Explainability in Machine Learning","created":"2022-10-24","cited_by_count":48,"area":null},{"id":"2212.03523","title":"Criteria for Classifying Forecasting Methods","created":"2022-12-07","cited_by_count":48,"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":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2103.14651","title":"Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice","created":"2021-03-27","cited_by_count":45,"area":null},{"id":"2106.06823","title":"Prompting Contrastive Explanations for Commonsense Reasoning Tasks","created":"2021-06-12","cited_by_count":45,"area":null},{"id":"2108.05149","title":"Logic Explained Networks","created":"2021-08-11","cited_by_count":45,"area":null},{"id":"2205.09971","title":"On Tackling Explanation Redundancy in Decision Trees","created":"2022-05-20","cited_by_count":44,"area":null},{"id":"2101.09429","title":"Explainable Artificial Intelligence Approaches: A Survey","created":"2021-01-23","cited_by_count":40,"area":null},{"id":"2105.06782","title":"SAT-Based Rigorous Explanations for Decision Lists","created":"2021-05-14","cited_by_count":40,"area":null},{"id":"2206.10847","title":"Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI","created":"2022-06-22","cited_by_count":40,"area":null},{"id":"2101.12446","title":"Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning","created":"2021-01-29","cited_by_count":39,"area":null},{"id":"2106.00154","title":"Explanations for Monotonic Classifiers","created":"2021-06-01","cited_by_count":39,"area":null},{"id":"2210.06959","title":"A Survey on Explainable Anomaly Detection","created":"2022-10-13","cited_by_count":39,"area":null},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2403.16812","title":"Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making","created":"2024-03-25","cited_by_count":38,"area":null},{"id":"2106.01350","title":"On Efficiently Explaining Graph-Based Classifiers","created":"2021-06-02","cited_by_count":37,"area":null},{"id":"2109.12480","title":"Explainability Pitfalls: Beyond Dark Patterns in Explainable AI","created":"2021-09-26","cited_by_count":36,"area":null},{"id":"2107.07015","title":"Do Humans Trust Advice More if it Comes from AI? An Analysis of Human-AI Interactions","created":"2021-07-14","cited_by_count":35,"area":null},{"id":"2103.08545","title":"A Study of Automatic Metrics for the Evaluation of Natural Language Explanations","created":"2021-03-15","cited_by_count":34,"area":null},{"id":"2306.01985","title":"COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements","created":"2023-06-03","cited_by_count":34,"area":null},{"id":"2203.15064","title":"Cycle-Consistent Counterfactuals by Latent Transformations","created":"2022-03-28","cited_by_count":33,"area":null},{"id":"2301.09937","title":"Explainable Deep Reinforcement Learning: State of the Art and Challenges","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2302.00799","title":"Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI","created":"2023-02-01","cited_by_count":33,"area":null},{"id":"2108.05276","title":"Trading Complexity for Sparsity in Random Forest Explanations","created":"2021-08-11","cited_by_count":32,"area":null},{"id":"2205.05057","title":"Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theory","created":"2022-05-10","cited_by_count":32,"area":null},{"id":"2309.03886","title":"FIND: A Function Description Benchmark for Evaluating Interpretability Methods","created":"2023-09-07","cited_by_count":32,"area":null},{"id":"2104.03483","title":"Question-Driven Design Process for Explainable AI User Experiences","created":"2021-04-08","cited_by_count":31,"area":null},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2110.08412","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","created":"2021-10-15","cited_by_count":31,"area":null},{"id":"2305.09770","title":"ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing","created":"2023-05-16","cited_by_count":31,"area":null},{"id":"2405.00722","title":"LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study","created":"2024-04-26","cited_by_count":31,"area":null},{"id":"2106.15231","title":"Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis","created":"2021-06-29","cited_by_count":30,"area":null}],"next_cursor":"100"}