{"total":877,"rows":[{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431,"area":null},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"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":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293,"area":null},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2106.13314","title":"Promises and Pitfalls of Black-Box Concept Learning Models","created":"2021-06-24","cited_by_count":131,"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":"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":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"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":"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":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"area":null},{"id":"2306.01574","title":"Probabilistic Concept Bottleneck Models","created":"2023-06-02","cited_by_count":101,"area":null},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","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":"2106.01613","title":"NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning","created":"2021-06-03","cited_by_count":88,"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":"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":"2202.01459","title":"Concept Bottleneck Model with Additional Unsupervised Concepts","created":"2022-02-03","cited_by_count":79,"area":null},{"id":"2212.07430","title":"Interactive Concept Bottleneck Models","created":"2022-12-14","cited_by_count":79,"area":null},{"id":"2212.11870","title":"Impossibility Theorems for Feature Attribution","created":"2022-12-22","cited_by_count":78,"area":null},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73,"area":null},{"id":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71,"area":null},{"id":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67,"area":null},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65,"area":null},{"id":"2210.07147","title":"Global Explainability of GNNs via Logic Combination of Learned Concepts","created":"2022-10-13","cited_by_count":65,"area":null},{"id":"2408.01432","title":"VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance","created":"2024-07-18","cited_by_count":65,"area":null},{"id":"2302.14260","title":"A Closer Look at the Intervention Procedure of Concept Bottleneck Models","created":"2023-02-28","cited_by_count":64,"area":null},{"id":"2305.06386","title":"Text-To-Concept (and Back) via Cross-Model Alignment","created":"2023-05-10","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":"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,"area":null},{"id":"2209.09056","title":"Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off","created":"2022-09-19","cited_by_count":61,"area":null},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2302.04269","title":"Diagnosing and Rectifying Vision Models using Language","created":"2023-02-08","cited_by_count":58,"area":null},{"id":"2209.11222","title":"Concept Activation Regions: A Generalized Framework For Concept-Based Explanations","created":"2022-09-22","cited_by_count":57,"area":null},{"id":"2304.14068","title":"Interpretable Neural-Symbolic Concept Reasoning","created":"2023-04-27","cited_by_count":57,"area":null},{"id":"2205.14120","title":"Neural Basis Models for Interpretability","created":"2022-05-27","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":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52,"area":null},{"id":"2106.06804","title":"Entropy-based Logic Explanations of Neural Networks","created":"2021-06-12","cited_by_count":51,"area":null},{"id":"2406.19272","title":"Stochastic Concept Bottleneck Models","created":"2024-06-27","cited_by_count":51,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2301.11911","title":"Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees","created":"2023-01-27","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":"2304.10131","title":"Learning Bottleneck Concepts in Image Classification","created":"2023-04-20","cited_by_count":49,"area":null},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"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":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","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":"2108.05149","title":"Logic Explained Networks","created":"2021-08-11","cited_by_count":45,"area":null},{"id":"2108.11761","title":"A Framework for Learning Ante-hoc Explainable Models via Concepts","created":"2021-08-25","cited_by_count":45,"area":null},{"id":"2103.12279","title":"SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers","created":"2021-03-23","cited_by_count":44,"area":null},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44,"area":null},{"id":"2302.00785","title":"SkinCon: A skin disease dataset densely annotated by domain experts for fine-grained model debugging and analysis","created":"2023-02-01","cited_by_count":44,"area":null},{"id":"2404.08978","title":"Incremental Residual Concept Bottleneck Models","created":"2024-04-13","cited_by_count":43,"area":null},{"id":"2412.07992","title":"Concept Bottleneck Large Language Models","created":"2024-12-11","cited_by_count":43,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42,"area":null},{"id":"2309.16928","title":"Learning to Receive Help: Intervention-Aware Concept Embedding Models","created":"2023-09-29","cited_by_count":41,"area":null},{"id":"2310.03182","title":"Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models","created":"2023-10-04","cited_by_count":40,"area":null},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40,"area":null},{"id":"2303.12872","title":"Human Uncertainty in Concept-Based AI Systems","created":"2023-03-22","cited_by_count":39,"area":null},{"id":"2106.02112","title":"Finding and Fixing Spurious Patterns with Explanations","created":"2021-06-03","cited_by_count":38,"area":null},{"id":"2209.11799","title":"Augmenting Interpretable Models with LLMs during Training","created":"2022-09-23","cited_by_count":38,"area":null},{"id":"2402.12240","title":"BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts","created":"2024-02-19","cited_by_count":37,"area":null},{"id":"2504.11524","title":"HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation","created":"2025-04-15","cited_by_count":37,"area":null},{"id":"2107.11889","title":"GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks","created":"2021-07-25","cited_by_count":35,"area":null},{"id":"2311.11108","title":"Auxiliary Losses for Learning Generalizable Concept-based Models","created":"2023-11-18","cited_by_count":35,"area":null},{"id":"2102.09099","title":"NuCLS: A scalable crowdsourcing, deep learning approach and dataset for nucleus classification, localization and segmentation","created":"2021-02-18","cited_by_count":34,"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":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"id":"2301.12276","title":"ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts","created":"2023-01-28","cited_by_count":33,"area":null},{"id":"2302.01242","title":"Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal","created":"2023-02-02","cited_by_count":33,"area":null},{"id":"2311.05014","title":"Interpreting Pretrained Language Models via Concept Bottlenecks","created":"2023-11-08","cited_by_count":33,"area":null},{"id":"2401.14142","title":"Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations","created":"2024-01-25","cited_by_count":33,"area":null},{"id":"2205.04766","title":"Explainable Deep Learning Methods in Medical Image Classification: A Survey","created":"2022-05-10","cited_by_count":32,"area":null},{"id":"2208.10609","title":"Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis","created":"2022-08-22","cited_by_count":32,"area":null},{"id":"2310.02116","title":"Coarse-to-Fine Concept Bottleneck Models","created":"2023-10-03","cited_by_count":31,"area":null},{"id":"2203.12892","title":"Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals","created":"2022-03-24","cited_by_count":30,"area":null},{"id":"2305.12696","title":"Learning Interpretable Style Embeddings via Prompting LLMs","created":"2023-05-22","cited_by_count":30,"area":null},{"id":"2209.14279","title":"Causal Proxy Models for Concept-Based Model Explanations","created":"2022-09-28","cited_by_count":29,"area":null},{"id":"2301.10367","title":"Towards Robust Metrics for Concept Representation Evaluation","created":"2023-01-25","cited_by_count":29,"area":null},{"id":"2308.13453","title":"Learning to Intervene on Concept Bottlenecks","created":"2023-08-25","cited_by_count":29,"area":null},{"id":"2405.16507","title":"Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning","created":"2024-05-26","cited_by_count":29,"area":null},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2401.13544","title":"Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2503.23283","title":"Language Guided Concept Bottleneck Models for Interpretable Continual Learning","created":"2025-03-30","cited_by_count":28,"area":null},{"id":"2207.04343","title":"Explaining Chest X-ray Pathologies in Natural Language","created":"2022-07-09","cited_by_count":27,"area":null},{"id":"2303.00885","title":"Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision","created":"2023-03-02","cited_by_count":27,"area":null},{"id":"2304.04579","title":"Coherent Concept-based Explanations in Medical Image and Its Application to Skin Lesion Diagnosis","created":"2023-04-10","cited_by_count":26,"area":null},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2205.14108","title":"Scalable Interpretability via Polynomials","created":"2022-05-27","cited_by_count":25,"area":null},{"id":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2312.15010","title":"SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology","created":"2023-12-22","cited_by_count":25,"area":null},{"id":"2112.02290","title":"Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations","created":"2021-12-04","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":"2303.07811","title":"ICICLE: Interpretable Class Incremental Continual Learning","created":"2023-03-14","cited_by_count":24,"area":null}],"next_cursor":"100"}