{"total":82,"rows":[{"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":"2305.16289","title":"Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation","created":"2023-05-25","cited_by_count":100,"area":null},{"id":"2212.04825","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","created":"2022-12-09","cited_by_count":85,"area":null},{"id":"2309.13415","title":"Dream the Impossible: Outlier Imagination with Diffusion Models","created":"2023-09-23","cited_by_count":77,"area":"diffusion"},{"id":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71,"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":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2302.04269","title":"Diagnosing and Rectifying Vision Models using Language","created":"2023-02-08","cited_by_count":58,"area":null},{"id":"2312.02974","title":"Describing Differences in Image Sets with Natural Language","created":"2023-12-05","cited_by_count":53,"area":null},{"id":"2304.03916","title":"Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning","created":"2023-04-08","cited_by_count":47,"area":null},{"id":"2305.19164","title":"LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images","created":"2023-05-30","cited_by_count":46,"area":null},{"id":"2208.08831","title":"Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning","created":"2022-08-18","cited_by_count":45,"area":null},{"id":"2212.02774","title":"Adaptive Testing of Computer Vision Models","created":"2022-12-06","cited_by_count":39,"area":null},{"id":"2306.12105","title":"Mass-Producing Failures of Multimodal Systems with Language Models","created":"2023-06-21","cited_by_count":36,"area":null},{"id":"2302.07865","title":"Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation","created":"2023-02-15","cited_by_count":35,"area":null},{"id":"2308.03977","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","created":"2023-08-08","cited_by_count":31,"area":null},{"id":"2211.12491","title":"ModelDiff: A Framework for Comparing Learning Algorithms","created":"2022-11-22","cited_by_count":30,"area":null},{"id":"2402.12550","title":"Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization","created":"2024-02-19","cited_by_count":28,"area":"moe"},{"id":"2309.17430","title":"FACTS: First Amplify Correlations and Then Slice to Discover Bias","created":"2023-09-29","cited_by_count":26,"area":null},{"id":"2302.10894","title":"Red Teaming Deep Neural Networks with Feature Synthesis Tools","created":"2023-02-08","cited_by_count":21,"area":"safety"},{"id":"2311.01007","title":"Effective Human-AI Teams via Learned Natural Language Rules and Onboarding","created":"2023-11-02","cited_by_count":20,"area":null},{"id":"2210.10769","title":"\"Why did the Model Fail?\": Attributing Model Performance Changes to Distribution Shifts","created":"2022-10-19","cited_by_count":18,"area":null},{"id":"2303.05072","title":"Identification of Systematic Errors of Image Classifiers on Rare Subgroups","created":"2023-03-09","cited_by_count":17,"area":null},{"id":"2406.12142","title":"Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods","created":"2024-06-17","cited_by_count":14,"area":null},{"id":"2306.08893","title":"LOVM: Language-Only Vision Model Selection","created":"2023-06-15","cited_by_count":12,"area":"mllm"},{"id":"2403.12777","title":"Discover and Mitigate Multiple Biased Subgroups in Image Classifiers","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2405.17299","title":"Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data","created":"2024-05-27","cited_by_count":11,"area":null},{"id":"2406.07145","title":"Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2501.16751","title":"HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging","created":"2025-01-28","cited_by_count":11,"area":null},{"id":"2311.15303","title":"Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement","created":"2023-11-26","cited_by_count":10,"area":null},{"id":"2403.02886","title":"Revisiting Confidence Estimation: Towards Reliable Failure Prediction","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2310.00164","title":"PRIME: Prioritizing Interpretability in Failure Mode Extraction","created":"2023-09-29","cited_by_count":9,"area":null},{"id":"2310.10461","title":"Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data","created":"2023-10-16","cited_by_count":8,"area":null},{"id":"2312.02548","title":"GeNIe: Generative Hard Negative Images Through Diffusion","created":"2023-12-05","cited_by_count":8,"area":"diffusion"},{"id":"2312.04712","title":"Error Discovery by Clustering Influence Embeddings","created":"2023-12-07","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":"2403.06606","title":"Distributionally Generative Augmentation for Fair Facial Attribute Classification","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2403.15309","title":"Controlled Training Data Generation with Diffusion Models","created":"2024-03-22","cited_by_count":8,"area":"diffusion"},{"id":"2410.22239","title":"DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2502.20375","title":"When does a predictor know its own loss?","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2503.18258","title":"Severing Spurious Correlations with Data Pruning","created":"2025-03-24","cited_by_count":7,"area":null},{"id":"2211.10024","title":"Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2310.13040","title":"Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2408.00331","title":"DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation","created":"2024-08-01","cited_by_count":6,"area":null},{"id":"2207.01059","title":"Identifying the Context Shift between Test Benchmarks and Production Data","created":"2022-07-03","cited_by_count":5,"area":null},{"id":"2402.14254","title":"A hierarchical decomposition for explaining ML performance discrepancies","created":"2024-02-22","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":"2408.04471","title":"What could go wrong? Discovering and describing failure modes in computer vision","created":"2024-08-08","cited_by_count":5,"area":null},{"id":"2505.03132","title":"VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis","created":"2025-05-06","cited_by_count":5,"area":null},{"id":"2305.03610","title":"The Role of Data Curation in Image Captioning","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2309.13489","title":"Identifying Systematic Errors in Object Detectors with the SCROD Pipeline","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2504.20902","title":"Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers","created":"2025-04-29","cited_by_count":4,"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":"2407.10633","title":"Evaluating Model Bias Requires Characterizing its Mistakes","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2503.17416","title":"Debugging and Runtime Analysis of Neural Networks with VLMs (A Case Study)","created":"2025-03-21","cited_by_count":3,"area":null},{"id":"2504.14523","title":"Learning from Reasoning Failures via Synthetic Data Generation","created":"2025-04-20","cited_by_count":2,"area":null},{"id":"2512.01048","title":"TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models","created":"2025-11-30","cited_by_count":2,"area":"mllm"},{"id":"2303.04862","title":"Deep Hypothesis Tests Detect Clinically Relevant Subgroup Shifts in Medical Images","created":"2023-03-08","cited_by_count":1,"area":null},{"id":"2311.06816","title":"On original and latent space connectivity in deep neural networks","created":"2023-11-12","cited_by_count":1,"area":null},{"id":"2312.05588","title":"Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs","created":"2023-12-09","cited_by_count":1,"area":null},{"id":"2312.06077","title":"An Ambiguity Measure for Recognizing the Unknowns in Deep Learning","created":"2023-12-11","cited_by_count":1,"area":null},{"id":"2502.12360","title":"Detecting Systematic Weaknesses in Vision Models along Predefined Human-Understandable Dimensions","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2504.17314","title":"Class-Conditional Distribution Balancing for Group Robust Classification","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2505.06831","title":"Fine-Grained Class-Conditional Distribution Balancing for Debiased Learning","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2505.11060","title":"CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2509.15551","title":"PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors","created":"2025-09-19","cited_by_count":1,"area":"safety"},{"id":"2511.19566","title":"ModHiFi: Identifying High Fidelity predictive components for Model Modification","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2602.06795","title":"Generating Data-Driven Reasoning Rubrics for Domain-Adaptive Reward Modeling","created":"2026-02-06","cited_by_count":1,"area":"lr"},{"id":"2603.02200","title":"Adaptive Confidence Regularization for Multimodal Failure Detection","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2404.07045","title":"Identification of Fine-grained Systematic Errors via Controlled Scene Generation","created":"2024-04-10","cited_by_count":0,"area":null},{"id":"2410.02512","title":"SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation","created":"2024-10-03","cited_by_count":0,"area":null},{"id":"2410.16738","title":"LLM-Assisted Red Teaming of Diffusion Models through \"Failures Are Fated, But Can Be Faded\"","created":"2024-10-22","cited_by_count":0,"area":"diffusion"},{"id":"2411.10845","title":"Automatic Discovery and Assessment of Interpretable Systematic Errors in Semantic Segmentation","created":"2024-11-16","cited_by_count":0,"area":null},{"id":"2412.15358","title":"Dataset Augmentation by Mixing Visual Concepts","created":"2024-12-19","cited_by_count":0,"area":"diffusion"},{"id":"2508.08701","title":"SafeFix: Targeted Model Repair via Controlled Image Generation","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2509.03616","title":"Multi Attribute Bias Mitigation via Representation Learning","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2512.24592","title":"GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2605.29836","title":"CB-SLICE: Concept-Based Interpretable Error Slice Discovery","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.15216","title":"Symbal: Detecting Systematic Misalignments in Model-Generated Captions","created":"2026-07-16","cited_by_count":0,"area":"mllm"},{"id":"2609.11126","title":"Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real World Conditions","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.12254","title":"Automated Detection and Structuring of Social Tipping Point Evidence in Climate related Documents: A Modular AI Framework","created":"2026-09-10","cited_by_count":0,"area":null}],"next_cursor":null}