{"total":23,"rows":[{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"area":null},{"id":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146,"area":null},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108,"area":null},{"id":"2107.00643","title":"Mandoline: Model Evaluation under Distribution Shift","created":"2021-07-01","cited_by_count":55,"area":null},{"id":"2109.11690","title":"Discovering and Validating AI Errors With Crowdsourced Failure Reports","created":"2021-09-23","cited_by_count":28,"area":null},{"id":"2305.14224","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2302.07346","title":"ScatterShot: Interactive In-context Example Curation for Text Transformation","created":"2023-02-14","cited_by_count":20,"area":null},{"id":"2402.14147","title":"Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia","created":"2024-02-21","cited_by_count":18,"area":null},{"id":"2309.03774","title":"Deep Learning Safety Concerns in Automated Driving Perception","created":"2023-09-07","cited_by_count":10,"area":null},{"id":"2309.06703","title":"VLSlice: Interactive Vision-and-Language Slice Discovery","created":"2023-09-13","cited_by_count":7,"area":null},{"id":"2108.05053","title":"Managing ML Pipelines: Feature Stores and the Coming Wave of Embedding Ecosystems","created":"2021-08-11","cited_by_count":6,"area":null},{"id":"2202.04166","title":"The Lifecycle of a Statistical Model: Model Failure Detection, Identification, and Refitting","created":"2022-02-08","cited_by_count":4,"area":null},{"id":"2104.13216","title":"Handling Long-Tail Queries with Slice-Aware Conversational Systems","created":"2021-04-26","cited_by_count":2,"area":null},{"id":"2408.10239","title":"A Conceptual Framework for Ethical Evaluation of Machine Learning Systems","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2204.06436","title":"Label Augmentation with Reinforced Labeling for Weak Supervision","created":"2022-04-13","cited_by_count":1,"area":null},{"id":"2212.09032","title":"AutoSlicer: Scalable Automated Data Slicing for ML Model Analysis","created":"2022-12-18","cited_by_count":1,"area":null},{"id":"2312.10366","title":"Fusing Conditional Submodular GAN and Programmatic Weak Supervision","created":"2023-12-16","cited_by_count":1,"area":null},{"id":"2505.05577","title":"PyTDC: A multimodal machine learning training, evaluation, and inference platform for biomedical foundation models","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2106.02363","title":"Learning Slice-Aware Representations with Mixture of Attentions","created":"2021-06-04","cited_by_count":0,"area":null},{"id":"2110.08430","title":"Metadata Shaping: Natural Language Annotations for the Tail","created":"2021-10-16","cited_by_count":0,"area":null},{"id":"2203.12023","title":"Generative Modeling Helps Weak Supervision (and Vice Versa)","created":"2022-03-22","cited_by_count":0,"area":null},{"id":"2503.02797","title":"A Causal Framework for Aligning Image Quality Metrics and Deep Neural Network Robustness","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2609.04197","title":"ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}