{"total":57,"rows":[{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293,"area":null},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243,"area":null},{"id":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221,"area":null},{"id":"2209.09858","title":"Extremely Simple Activation Shaping for Out-of-Distribution Detection","created":"2022-09-20","cited_by_count":212,"area":null},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190,"area":null},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"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":"2405.16833","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","created":"2024-05-27","cited_by_count":125,"area":null},{"id":"2310.04742","title":"Parameter Efficient Multi-task Model Fusion with Partial Linearization","created":"2023-10-07","cited_by_count":65,"area":null},{"id":"2311.11908","title":"Continual Learning: Applications and the Road Forward","created":"2023-11-20","cited_by_count":59,"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":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"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":"2210.09520","title":"Using Language to Extend to Unseen Domains","created":"2022-10-18","cited_by_count":34,"area":null},{"id":"2406.11194","title":"In-Context Editing: Learning Knowledge from Self-Induced Distributions","created":"2024-06-17","cited_by_count":34,"area":null},{"id":"2306.00738","title":"ReFACT: Updating Text-to-Image Models by Editing the Text Encoder","created":"2023-06-01","cited_by_count":32,"area":null},{"id":"2207.04806","title":"Repairing Neural Networks by Leaving the Right Past Behind","created":"2022-07-11","cited_by_count":27,"area":null},{"id":"2205.12677","title":"Language Anisotropic Cross-Lingual Model Editing","created":"2022-05-25","cited_by_count":26,"area":null},{"id":"2207.14288","title":"Rewriting Geometric Rules of a GAN","created":"2022-07-28","cited_by_count":25,"area":null},{"id":"2308.12462","title":"Overcoming Generic Knowledge Loss with Selective Parameter Update","created":"2023-08-23","cited_by_count":23,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2409.13456","title":"Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?","created":"2024-09-20","cited_by_count":18,"area":null},{"id":"2407.03921","title":"Concept Bottleneck Models Without Predefined Concepts","created":"2024-07-04","cited_by_count":17,"area":null},{"id":"2311.08011","title":"Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models","created":"2023-11-14","cited_by_count":15,"area":null},{"id":"2407.07089","title":"Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic","created":"2024-07-09","cited_by_count":14,"area":null},{"id":"2302.12480","title":"Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?","created":"2023-02-24","cited_by_count":13,"area":null},{"id":"2208.09756","title":"Artifact-Based Domain Generalization of Skin Lesion Models","created":"2022-08-20","cited_by_count":11,"area":null},{"id":"2310.10591","title":"Interpreting and Controlling Vision Foundation Models via Text Explanations","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2310.01685","title":"A Framework for Interpretability in Machine Learning for Medical Imaging","created":"2023-10-02","cited_by_count":9,"area":null},{"id":"2303.00046","title":"Edit at your own risk: evaluating the robustness of edited models to distribution shifts","created":"2023-02-28","cited_by_count":8,"area":null},{"id":"2402.03715","title":"Clarify: Improving Model Robustness With Natural Language Corrections","created":"2024-02-06","cited_by_count":8,"area":null},{"id":"2205.06905","title":"Perspectives on Incorporating Expert Feedback into Model Updates","created":"2022-05-13","cited_by_count":7,"area":null},{"id":"2211.13317","title":"Rank-One Editing of Encoder-Decoder Models","created":"2022-11-23","cited_by_count":7,"area":null},{"id":"2406.18534","title":"Towards Compositionality in Concept Learning","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2206.13498","title":"Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior","created":"2022-06-27","cited_by_count":5,"area":null},{"id":"2404.09601","title":"Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2406.16846","title":"Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection","created":"2024-06-24","cited_by_count":5,"area":null},{"id":"2411.01948","title":"Learning Where to Edit Vision Transformers","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2501.05714","title":"How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyond","created":"2025-01-10","cited_by_count":4,"area":null},{"id":"2211.09859","title":"Data-Centric Debugging: mitigating model failures via targeted data collection","created":"2022-11-17","cited_by_count":3,"area":null},{"id":"2312.05464","title":"Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generation","created":"2023-12-09","cited_by_count":3,"area":null},{"id":"2603.15656","title":"Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2305.14122","title":"Transferring Learning Trajectories of Neural Networks","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2401.12540","title":"DREditor: An Time-efficient Approach for Building a Domain-specific Dense Retrieval Model","created":"2024-01-23","cited_by_count":2,"area":null},{"id":"2501.13818","title":"Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2604.02719","title":"MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2210.03879","title":"Improving Data-Efficient Fossil Segmentation via Model Editing","created":"2022-10-08","cited_by_count":1,"area":null},{"id":"2404.04814","title":"Inference-Time Rule Eraser: Fair Recognition via Distilling and Removing Biased Rules","created":"2024-04-07","cited_by_count":1,"area":null},{"id":"2510.11268","title":"Exploring and Leveraging Class Vectors for Classifier Editing","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2211.15060","title":"Interactive Visual Feature Search","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2303.14772","title":"$\\Delta$-Patching: A Framework for Rapid Adaptation of Pre-trained Convolutional Networks without Base Performance Loss","created":"2023-03-26","cited_by_count":0,"area":null},{"id":"2303.16564","title":"Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network","created":"2023-03-29","cited_by_count":0,"area":null},{"id":"2402.04440","title":"Exploring higher-order neural network node interactions with total correlation","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2407.15756","title":"Model editing for distribution shifts in uranium oxide morphological analysis","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2602.16545","title":"Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding","created":"2026-02-18","cited_by_count":0,"area":null}],"next_cursor":null}