{"total":18,"rows":[{"id":"2311.13594","title":"Labeling Neural Representations with Inverse Recognition","created":"2023-11-22","cited_by_count":32,"area":null},{"id":"2401.13536","title":"Finetuning Foundation Models for Joint Analysis Optimization","created":"2024-01-24","cited_by_count":18,"area":null},{"id":"2503.15234","title":"CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification","created":"2025-03-19","cited_by_count":9,"area":null},{"id":"2406.08572","title":"LLM-assisted Concept Discovery: Automatically Identifying and Explaining Neuron Functions","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2307.06913","title":"Uncovering Unique Concept Vectors through Latent Space Decomposition","created":"2023-07-13","cited_by_count":5,"area":null},{"id":"2502.16105","title":"NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2602.23947","title":"Hierarchical Concept-based Interpretable Models","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2310.04519","title":"SPADE: Sparsity-Guided Debugging for Deep Neural Networks","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2411.10019","title":"Towards Utilising a Range of Neural Activations for Comprehending Representational Associations","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2510.15520","title":"Discovering Intersectional Bias via Directional Alignment in Face Recognition Embeddings","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2603.09787","title":"What is Missing? Explaining Neurons Activated by Absent Concepts","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2605.12809","title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2505.07831","title":"Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2511.20931","title":"Open Vocabulary Compositional Explanations for Neuron Alignment","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2511.20934","title":"Guaranteed Optimal Compositional Explanations for Neurons","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2605.31304","title":"Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.15731","title":"Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification","created":"2026-08-16","cited_by_count":0,"area":null}],"next_cursor":null}