{"total":34,"rows":[{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2406.08391","title":"Large Language Models Must Be Taught to Know What They Don't Know","created":"2024-06-12","cited_by_count":100,"area":null},{"id":"2406.19272","title":"Stochastic Concept Bottleneck Models","created":"2024-06-27","cited_by_count":51,"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":"2402.12240","title":"BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts","created":"2024-02-19","cited_by_count":37,"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":"2308.13453","title":"Learning to Intervene on Concept Bottlenecks","created":"2023-08-25","cited_by_count":29,"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":"2502.20502","title":"On Benchmarking Human-Like Intelligence in Machines","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2310.19660","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2501.19047","title":"Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)","created":"2025-01-31","cited_by_count":20,"area":null},{"id":"2304.06701","title":"Learning Personalized Decision Support Policies","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2405.18217","title":"Understanding Inter-Concept Relationships in Concept-Based Models","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2401.01259","title":"Do Concept Bottleneck Models Respect Localities?","created":"2024-01-02","cited_by_count":10,"area":null},{"id":"2504.17921","title":"Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts","created":"2025-04-24","cited_by_count":9,"area":null},{"id":"2403.14566","title":"A survey on Concept-based Approaches For Model Improvement","created":"2024-03-21","cited_by_count":8,"area":null},{"id":"2306.08424","title":"Selective Concept Models: Permitting Stakeholder Customisation at Test-Time","created":"2023-06-14","cited_by_count":6,"area":null},{"id":"2411.04342","title":"Classification with Conceptual Safeguards","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2508.00545","title":"Foundations of Interpretable Models","created":"2025-08-01","cited_by_count":4,"area":null},{"id":"2601.12913","title":"Actionable Interpretability Must Be Defined in Terms of Symmetries","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2402.14726","title":"Incorporating Expert Rules into Neural Networks in the Framework of Concept-Based Learning","created":"2024-02-22","cited_by_count":3,"area":null},{"id":"2503.11381","title":"Modeling Subjectivity in Cognitive Appraisal with Language Models","created":"2025-03-14","cited_by_count":3,"area":null},{"id":"2310.03283","title":"A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2501.10476","title":"Revisiting Rogers' Paradox in the Context of Human-AI Interaction","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2312.08063","title":"Estimation of Concept Explanations Should be Uncertainty Aware","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2403.05576","title":"Understanding Subjectivity through the Lens of Motivational Context in Model-Generated Image Satisfaction","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2408.01935","title":"Defining and Evaluating Decision and Composite Risk in Language Models Applied to Natural Language Inference","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2502.20393","title":"Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2510.01220","title":"Towards Open-Ended Discovery for Low-Resource NLP","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2604.19323","title":"Concept Inconsistency in Dermoscopic Concept Bottleneck Models: A Rough-Set Analysis of the Derm7pt Dataset","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2604.24170","title":"Credal Concept Bottleneck Models for Epistemic-Aleatoric Uncertainty Decomposition","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.18648","title":"An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.04326","title":"Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.10669","title":"In Defense of Information Leakage in Concept-based Models","created":"2026-06-09","cited_by_count":0,"area":null}],"next_cursor":null}