{"total":508,"rows":[{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336,"area":"mllm"},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327,"area":"lr"},{"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":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288,"area":"lr"},{"id":"2202.01602","title":"The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":159,"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":"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":"2101.04719","title":"Expanding Explainability: Towards Social Transparency in AI systems","created":"2021-01-12","cited_by_count":124,"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":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"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":"2108.11195","title":"Lizard: A Large-Scale Dataset for Colonic Nuclear Instance Segmentation and Classification","created":"2021-08-25","cited_by_count":89,"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":"2307.08678","title":"Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations","created":"2023-07-17","cited_by_count":85,"area":null},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","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":"2204.11788","title":"Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation","created":"2022-04-25","cited_by_count":67,"area":null},{"id":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67,"area":null},{"id":"2104.14362","title":"From Distributed Machine Learning to Federated Learning: A Survey","created":"2021-04-29","cited_by_count":66,"area":null},{"id":"2105.02968","title":"This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks","created":"2021-05-05","cited_by_count":65,"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":"2402.01881","title":"Large Language Model Agent for Hyper-Parameter Optimization","created":"2024-02-02","cited_by_count":64,"area":"agents"},{"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":"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":"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":"2312.14183","title":"On Early Detection of Hallucinations in Factual Question Answering","created":"2023-12-19","cited_by_count":56,"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":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2104.12669","title":"Exploiting Explanations for Model Inversion Attacks","created":"2021-04-26","cited_by_count":49,"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":"2108.13654","title":"Discretized Integrated Gradients for Explaining Language Models","created":"2021-08-31","cited_by_count":46,"area":null},{"id":"2207.09615","title":"Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability","created":"2022-07-20","cited_by_count":46,"area":null},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2108.05149","title":"Logic Explained Networks","created":"2021-08-11","cited_by_count":45,"area":null},{"id":"2111.14485","title":"CoNIC: Colon Nuclei Identification and Counting Challenge 2022","created":"2021-11-29","cited_by_count":45,"area":null},{"id":"2407.10114","title":"TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation","created":"2024-07-14","cited_by_count":42,"area":null},{"id":"2103.02354","title":"Evaluating Robustness of Counterfactual Explanations","created":"2021-03-03","cited_by_count":41,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2101.09429","title":"Explainable Artificial Intelligence Approaches: A Survey","created":"2021-01-23","cited_by_count":40,"area":null},{"id":"2111.09094","title":"STEEX: Steering Counterfactual Explanations with Semantics","created":"2021-11-17","cited_by_count":40,"area":null},{"id":"2205.07277","title":"Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations","created":"2022-05-15","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":"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":"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":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2104.04128","title":"An Empirical Comparison of Instance Attribution Methods for NLP","created":"2021-04-09","cited_by_count":35,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2107.13782","title":"Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions","created":"2021-07-29","cited_by_count":35,"area":null},{"id":"2207.12213","title":"On Computing Probabilistic Explanations for Decision Trees","created":"2022-06-30","cited_by_count":35,"area":null},{"id":"2303.09778","title":"SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization","created":"2023-03-17","cited_by_count":35,"area":null},{"id":"2306.08107","title":"AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks","created":"2023-06-13","cited_by_count":35,"area":null},{"id":"2403.14680","title":"Trust in AI: Progress, Challenges, and Future Directions","created":"2024-03-12","cited_by_count":35,"area":null},{"id":"2203.02013","title":"DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations","created":"2022-03-03","cited_by_count":34,"area":null},{"id":"2403.10415","title":"Gradient based Feature Attribution in Explainable AI: A Technical Review","created":"2024-03-15","cited_by_count":34,"area":null},{"id":"2106.08640","title":"Counterfactual Graphs for Explainable Classification of Brain Networks","created":"2021-06-16","cited_by_count":33,"area":null},{"id":"2107.07045","title":"Explainable AI: current status and future directions","created":"2021-07-12","cited_by_count":33,"area":null},{"id":"2104.14995","title":"Interpretable Semantic Photo Geolocation","created":"2021-04-30","cited_by_count":32,"area":null},{"id":"2311.13594","title":"Labeling Neural Representations with Inverse Recognition","created":"2023-11-22","cited_by_count":32,"area":null},{"id":"2104.05433","title":"Multilingual Language Models Predict Human Reading Behavior","created":"2021-04-12","cited_by_count":29,"area":null},{"id":"2212.11737","title":"The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations","created":"2022-12-22","cited_by_count":29,"area":null},{"id":"2301.09656","title":"Selective Explanations: Leveraging Human Input to Align Explainable AI","created":"2023-01-23","cited_by_count":29,"area":null},{"id":"2109.00520","title":"The Role of Explainability in Assuring Safety of Machine Learning in Healthcare","created":"2021-09-01","cited_by_count":26,"area":null},{"id":"2110.02376","title":"Foundations of Symbolic Languages for Model Interpretability","created":"2021-10-05","cited_by_count":26,"area":null},{"id":"2108.01174","title":"Knowledge-intensive Language Understanding for Explainable AI","created":"2021-08-02","cited_by_count":25,"area":null},{"id":"2207.06236","title":"Explainable Intrusion Detection Systems (X-IDS): A Survey of Current Methods, Challenges, and Opportunities","created":"2022-07-13","cited_by_count":25,"area":null},{"id":"2209.11812","title":"Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making","created":"2022-09-23","cited_by_count":25,"area":null},{"id":"2505.17120","title":"Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions","created":"2025-05-21","cited_by_count":25,"area":null},{"id":"2103.01451","title":"Explainable Person Re-Identification with Attribute-guided Metric Distillation","created":"2021-03-02","cited_by_count":24,"area":null},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2206.04394","title":"Xplique: A Deep Learning Explainability Toolbox","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2304.04780","title":"A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?","created":"2023-04-10","cited_by_count":24,"area":null},{"id":"2305.02279","title":"Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models","created":"2023-05-03","cited_by_count":24,"area":null},{"id":"2406.01382","title":"Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function","created":"2024-06-03","cited_by_count":24,"area":null},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2102.00625","title":"Human Perceptions on Moral Responsibility of AI: A Case Study in AI-Assisted Bail Decision-Making","created":"2021-02-01","cited_by_count":23,"area":null},{"id":"2202.11479","title":"Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF","created":"2022-02-23","cited_by_count":23,"area":null},{"id":"2204.10806","title":"A Taxonomy of Human and ML Strengths in Decision-Making to Investigate Human-ML Complementarity","created":"2022-04-22","cited_by_count":23,"area":null},{"id":"2212.09360","title":"AI Security for Geoscience and Remote Sensing: Challenges and Future Trends","created":"2022-12-19","cited_by_count":23,"area":null},{"id":"2301.08912","title":"Rationalization for Explainable NLP: A Survey","created":"2023-01-21","cited_by_count":22,"area":null},{"id":"2310.08043","title":"Understanding and Controlling a Maze-Solving Policy Network","created":"2023-10-12","cited_by_count":22,"area":null},{"id":"2103.13726","title":"Variational Autoencoder-Based Vehicle Trajectory Prediction with an Interpretable Latent Space","created":"2021-03-25","cited_by_count":21,"area":null},{"id":"2101.03970","title":"How Much Automation Does a Data Scientist Want?","created":"2021-01-07","cited_by_count":20,"area":null},{"id":"2102.11115","title":"Probing Multimodal Embeddings for Linguistic Properties: the Visual-Semantic Case","created":"2021-02-22","cited_by_count":20,"area":null},{"id":"2109.15035","title":"Focus! Rating XAI Methods and Finding Biases","created":"2021-09-28","cited_by_count":20,"area":null},{"id":"2203.13909","title":"Concept Embedding Analysis: A Review","created":"2022-03-25","cited_by_count":20,"area":null},{"id":"2205.03931","title":"Write It Like You See It: Detectable Differences in Clinical Notes By Race Lead To Differential Model Recommendations","created":"2022-05-08","cited_by_count":20,"area":null},{"id":"2211.06753","title":"Seamful XAI: Operationalizing Seamful Design in Explainable AI","created":"2022-11-12","cited_by_count":20,"area":null},{"id":"2212.08104","title":"The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies","created":"2022-12-08","cited_by_count":20,"area":null},{"id":"2512.19941","title":"Block-Recurrent Dynamics in Vision Transformers","created":"2025-12-23","cited_by_count":20,"area":null},{"id":"2108.01182","title":"Underreporting of errors in NLG output, and what to do about it","created":"2021-08-02","cited_by_count":19,"area":null},{"id":"2109.04552","title":"SPECTRA: Sparse Structured Text Rationalization","created":"2021-09-09","cited_by_count":19,"area":null},{"id":"2307.05471","title":"Scale Alone Does not Improve Mechanistic Interpretability in Vision Models","created":"2023-07-11","cited_by_count":18,"area":"mechinterp"}],"next_cursor":"100"}