{"total":5070,"rows":[{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724,"area":"mechinterp"},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611,"area":"lr"},{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491,"area":null},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381,"area":null},{"id":"2210.14896","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","created":"2022-10-26","cited_by_count":379,"area":"diffusion"},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327,"area":"lr"},{"id":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312,"area":null},{"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":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288,"area":"lr"},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285,"area":null},{"id":"2310.01957","title":"Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving","created":"2023-10-03","cited_by_count":232,"area":"driving"},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"area":null},{"id":"2211.13445","title":"Delving into Out-of-Distribution Detection with Vision-Language Representations","created":"2022-11-24","cited_by_count":216,"area":null},{"id":"2108.00941","title":"A Survey of Human-in-the-loop for Machine Learning","created":"2021-08-02","cited_by_count":215,"area":null},{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2209.06243","title":"CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task","created":"2022-09-13","cited_by_count":207,"area":null},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186,"area":"safety"},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"area":null},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"area":null},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172,"area":null},{"id":"2202.06861","title":"Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond","created":"2022-02-14","cited_by_count":171,"area":null},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169,"area":"lr"},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163,"area":null},{"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":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2203.14960","title":"Domino: Discovering Systematic Errors with Cross-Modal Embeddings","created":"2022-03-24","cited_by_count":156,"area":null},{"id":"2107.10912","title":"Explainable artificial intelligence (XAI) in deep learning-based medical image analysis","created":"2021-07-22","cited_by_count":147,"area":null},{"id":"2210.13701","title":"Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence","created":"2022-10-25","cited_by_count":144,"area":null},{"id":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141,"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":"2112.03052","title":"Scaling Up Influence Functions","created":"2021-12-06","cited_by_count":132,"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":"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":"2106.12620","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","created":"2021-06-23","cited_by_count":127,"area":null},{"id":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","cited_by_count":126,"area":null},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","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":"2110.10790","title":"Human-Centered Explainable AI (XAI): From Algorithms to User Experiences","created":"2021-10-20","cited_by_count":123,"area":null},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","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":"2305.14902","title":"M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection","created":"2023-05-24","cited_by_count":121,"area":null},{"id":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120,"area":null},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"area":"lr"},{"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":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","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":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2105.04289","title":"Do Concept Bottleneck Models Learn as Intended?","created":"2021-05-10","cited_by_count":116,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2207.07605","title":"Algorithms to estimate Shapley value feature attributions","created":"2022-07-15","cited_by_count":115,"area":null},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114,"area":null},{"id":"2106.02666","title":"Counterfactual Explanations Can Be Manipulated","created":"2021-06-04","cited_by_count":113,"area":null},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108,"area":null},{"id":"2104.08762","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","created":"2021-04-18","cited_by_count":107,"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":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104,"area":null},{"id":"2305.08809","title":"Interpretability at Scale: Identifying Causal Mechanisms in Alpaca","created":"2023-05-15","cited_by_count":103,"area":null},{"id":"2102.13620","title":"Towards Robust and Reliable Algorithmic Recourse","created":"2021-02-26","cited_by_count":102,"area":null},{"id":"2106.09788","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","created":"2021-06-17","cited_by_count":102,"area":null},{"id":"2202.00449","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","created":"2022-02-01","cited_by_count":102,"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":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98,"area":null},{"id":"2112.04417","title":"What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods","created":"2021-12-06","cited_by_count":98,"area":null},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"area":null},{"id":"2409.00729","title":"ContextCite: Attributing Model Generation to Context","created":"2024-09-01","cited_by_count":98,"area":null},{"id":"2112.02902","title":"Interpretable Image Classification with Differentiable Prototypes Assignment","created":"2021-12-06","cited_by_count":97,"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":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","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":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91,"area":"mechinterp"},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90,"area":"lr"},{"id":"2205.07424","title":"Trustworthy Graph Neural Networks: Aspects, Methods and Trends","created":"2022-05-16","cited_by_count":89,"area":null},{"id":"2205.10268","title":"B-cos Networks: Alignment is All We Need for Interpretability","created":"2022-05-20","cited_by_count":88,"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":"2108.12237","title":"Evaluating the Robustness of Neural Language Models to Input Perturbations","created":"2021-08-27","cited_by_count":87,"area":null},{"id":"2108.00783","title":"CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms","created":"2021-08-02","cited_by_count":86,"area":null},{"id":"2109.05184","title":"MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets","created":"2021-09-11","cited_by_count":86,"area":null},{"id":"2112.11471","title":"Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies","created":"2021-12-21","cited_by_count":86,"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":"2111.02398","title":"Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods","created":"2021-11-01","cited_by_count":83,"area":null},{"id":"2203.08410","title":"Thinking about GPT-3 In-Context Learning for Biomedical IE? Think Again","created":"2022-03-16","cited_by_count":83,"area":"lr"},{"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}],"next_cursor":"100"}