{"total":246,"rows":[{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832,"area":"synth"},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395,"area":null},{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203,"area":null},{"id":"2210.02441","title":"Ask Me Anything: A simple strategy for prompting language models","created":"2022-10-05","cited_by_count":155,"area":null},{"id":"2109.11377","title":"WRENCH: A Comprehensive Benchmark for Weak Supervision","created":"2021-09-23","cited_by_count":96,"area":null},{"id":"2202.05433","title":"A Survey on Programmatic Weak Supervision","created":"2022-02-11","cited_by_count":66,"area":null},{"id":"2205.02318","title":"Language Models in the Loop: Incorporating Prompting into Weak Supervision","created":"2022-05-04","cited_by_count":52,"area":null},{"id":"2405.16043","title":"Theoretical Analysis of Weak-to-Strong Generalization","created":"2024-05-25","cited_by_count":48,"area":null},{"id":"2111.04578","title":"Improved Regularization and Robustness for Fine-tuning in Neural Networks","created":"2021-11-08","cited_by_count":45,"area":null},{"id":"2301.04819","title":"Data-centric AI: Perspectives and Challenges","created":"2023-01-12","cited_by_count":43,"area":null},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38,"area":null},{"id":"2104.08656","title":"Learning from Noisy Labels for Entity-Centric Information Extraction","created":"2021-04-17","cited_by_count":34,"area":null},{"id":"2107.02233","title":"End-to-End Weak Supervision","created":"2021-07-05","cited_by_count":33,"area":null},{"id":"2112.07184","title":"Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation","created":"2021-12-14","cited_by_count":33,"area":null},{"id":"2412.04692","title":"Smoothie: Label Free Language Model Routing","created":"2024-12-06","cited_by_count":31,"area":null},{"id":"2107.06997","title":"DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Search","created":"2021-07-05","cited_by_count":29,"area":null},{"id":"2206.07181","title":"To Aggregate or Not? Learning with Separate Noisy Labels","created":"2022-06-14","cited_by_count":29,"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":"2112.03865","title":"Universalizing Weak Supervision","created":"2021-12-07","cited_by_count":27,"area":null},{"id":"2207.02849","title":"Betty: An Automatic Differentiation Library for Multilevel Optimization","created":"2022-07-05","cited_by_count":27,"area":null},{"id":"2110.02591","title":"Weakly-supervised Text Classification Based on Keyword Graph","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2210.01078","title":"Unsupervised Model Selection for Time-series Anomaly Detection","created":"2022-10-03","cited_by_count":25,"area":null},{"id":"2403.00165","title":"TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision","created":"2024-02-29","cited_by_count":25,"area":null},{"id":"2106.06235","title":"Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks","created":"2021-06-11","cited_by_count":24,"area":null},{"id":"2112.06439","title":"What can Data-Centric AI Learn from Data and ML Engineering?","created":"2021-12-13","cited_by_count":24,"area":null},{"id":"2202.00828","title":"Co-training Improves Prompt-based Learning for Large Language Models","created":"2022-02-02","cited_by_count":24,"area":null},{"id":"2506.18203","title":"Shrinking the Generation-Verification Gap with Weak Verifiers","created":"2025-06-22","cited_by_count":24,"area":null},{"id":"2105.08149","title":"Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments","created":"2021-05-17","cited_by_count":23,"area":null},{"id":"2204.09371","title":"Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification","created":"2022-04-20","cited_by_count":21,"area":null},{"id":"2412.03881","title":"Weak-to-Strong Generalization Through the Data-Centric Lens","created":"2024-12-05","cited_by_count":21,"area":"alignment"},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2303.14582","title":"Identification of Negative Transfers in Multitask Learning Using Surrogate Models","created":"2023-03-25","cited_by_count":20,"area":null},{"id":"2206.02914","title":"Training Subset Selection for Weak Supervision","created":"2022-06-06","cited_by_count":19,"area":null},{"id":"2105.05699","title":"Automating Data Science: Prospects and Challenges","created":"2021-05-12","cited_by_count":18,"area":null},{"id":"2110.13740","title":"DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples","created":"2021-10-26","cited_by_count":18,"area":null},{"id":"2309.13734","title":"Prompting and Fine-Tuning Open-Sourced Large Language Models for Stance Classification","created":"2023-09-24","cited_by_count":17,"area":null},{"id":"2310.05674","title":"Making Scalable Meta Learning Practical","created":"2023-10-09","cited_by_count":17,"area":null},{"id":"2207.13545","title":"Learning Hyper Label Model for Programmatic Weak Supervision","created":"2022-07-27","cited_by_count":16,"area":null},{"id":"2105.12848","title":"BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition","created":"2021-05-26","cited_by_count":15,"area":null},{"id":"2109.02102","title":"Teaching Autoregressive Language Models Complex Tasks By Demonstration","created":"2021-09-05","cited_by_count":15,"area":null},{"id":"2204.08892","title":"A survey on improving NLP models with human explanations","created":"2022-04-19","cited_by_count":15,"area":null},{"id":"2101.09763","title":"Analysing the Noise Model Error for Realistic Noisy Label Data","created":"2021-01-24","cited_by_count":14,"area":null},{"id":"2106.04530","title":"Learning from Multiple Noisy Partial Labelers","created":"2021-06-08","cited_by_count":14,"area":null},{"id":"2107.11413","title":"An Instance-Dependent Simulation Framework for Learning with Label Noise","created":"2021-07-23","cited_by_count":14,"area":null},{"id":"2110.03484","title":"Creating Training Sets via Weak Indirect Supervision","created":"2021-10-07","cited_by_count":14,"area":null},{"id":"2211.05764","title":"DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systems","created":"2022-11-09","cited_by_count":14,"area":null},{"id":"2309.07601","title":"Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals","created":"2023-09-14","cited_by_count":14,"area":null},{"id":"2109.13770","title":"Micromodels for Efficient, Explainable, and Reusable Systems: A Case Study on Mental Health","created":"2021-09-28","cited_by_count":13,"area":null},{"id":"2310.05632","title":"Binary Classification with Confidence Difference","created":"2023-10-09","cited_by_count":13,"area":null},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2102.00036","title":"Facilitating Knowledge Sharing from Domain Experts to Data Scientists for Building NLP Models","created":"2021-01-29","cited_by_count":12,"area":null},{"id":"2104.14847","title":"Active WeaSuL: Improving Weak Supervision with Active Learning","created":"2021-04-30","cited_by_count":12,"area":null},{"id":"2111.07392","title":"Edge-Native Intelligence for 6G Communications Driven by Federated Learning: A Survey of Trends and Challenges","created":"2021-11-14","cited_by_count":12,"area":null},{"id":"2112.07337","title":"Multi-Row, Multi-Span Distant Supervision For Table+Text Question","created":"2021-12-14","cited_by_count":12,"area":null},{"id":"2109.11410","title":"Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programming","created":"2021-09-23","cited_by_count":11,"area":null},{"id":"2206.09315","title":"Knowledge Learning with Crowdsourcing: A Brief Review and Systematic Perspective","created":"2022-06-19","cited_by_count":11,"area":null},{"id":"2212.06921","title":"Losses over Labels: Weakly Supervised Learning via Direct Loss Construction","created":"2022-12-13","cited_by_count":11,"area":null},{"id":"2305.11779","title":"DMDD: A Large-Scale Dataset for Dataset Mentions Detection","created":"2023-05-19","cited_by_count":11,"area":null},{"id":"2203.01382","title":"Nemo: Guiding and Contextualizing Weak Supervision for Interactive Data Programming","created":"2022-03-02","cited_by_count":10,"area":null},{"id":"2211.13375","title":"Lifting Weak Supervision To Structured Prediction","created":"2022-11-24","cited_by_count":10,"area":null},{"id":"2302.07560","title":"Unsupervised classification to improve the quality of a bird song recording dataset","created":"2023-02-15","cited_by_count":10,"area":null},{"id":"2407.11004","title":"The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators","created":"2024-06-25","cited_by_count":10,"area":null},{"id":"2106.00162","title":"HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations","created":"2021-06-01","cited_by_count":9,"area":null},{"id":"2210.03594","title":"Label Propagation with Weak Supervision","created":"2022-10-07","cited_by_count":9,"area":null},{"id":"2307.10586","title":"A Holistic Assessment of the Reliability of Machine Learning Systems","created":"2023-07-20","cited_by_count":9,"area":null},{"id":"2412.03854","title":"What Do Machine Learning Researchers Mean by \"Reproducible\"?","created":"2024-12-05","cited_by_count":9,"area":null},{"id":"2201.02936","title":"Weak Supervision for Affordable Modeling of Electrocardiogram Data","created":"2022-01-09","cited_by_count":8,"area":null},{"id":"2202.14000","title":"Resolving label uncertainty with implicit posterior models","created":"2022-02-28","cited_by_count":8,"area":null},{"id":"2205.12879","title":"Understanding Programmatic Weak Supervision via Source-aware Influence Function","created":"2022-05-25","cited_by_count":8,"area":null},{"id":"2303.14496","title":"Learning with Explanation Constraints","created":"2023-03-25","cited_by_count":8,"area":null},{"id":"2305.18623","title":"Alfred: A System for Prompted Weak Supervision","created":"2023-05-29","cited_by_count":8,"area":null},{"id":"2309.06503","title":"Leveraging Large Language Models and Weak Supervision for Social Media data annotation: an evaluation using COVID-19 self-reported vaccination tweets","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2403.12167","title":"A Systematic Review of Generalization Research in Medical Image Classification","created":"2024-03-18","cited_by_count":8,"area":null},{"id":"2506.10908","title":"Probably Approximately Correct Labels","created":"2025-06-12","cited_by_count":8,"area":null},{"id":"2509.10697","title":"A Survey on Retrieval And Structuring Augmented Generation with Large Language Models","created":"2025-09-12","cited_by_count":8,"area":null},{"id":"2101.07769","title":"A System for Automated Open-Source Threat Intelligence Gathering and Management","created":"2021-01-19","cited_by_count":7,"area":null},{"id":"2103.02761","title":"Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation","created":"2021-03-03","cited_by_count":7,"area":null},{"id":"2206.12088","title":"Classifying Unstructured Clinical Notes via Automatic Weak Supervision","created":"2022-06-24","cited_by_count":7,"area":null},{"id":"2208.14362","title":"AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels","created":"2022-08-30","cited_by_count":7,"area":null},{"id":"2210.03092","title":"Adaptive Ranking-based Sample Selection for Weakly Supervised Class-imbalanced Text Classification","created":"2022-10-06","cited_by_count":7,"area":null},{"id":"2308.00401","title":"VideoPro: A Visual Analytics Approach for Interactive Video Programming","created":"2023-08-01","cited_by_count":7,"area":null},{"id":"2406.10292","title":"Automatically Labeling Clinical Trial Outcomes: A Large-Scale Benchmark for Drug Development","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2106.10302","title":"Dependency Structure Misspecification in Multi-Source Weak Supervision Models","created":"2021-06-18","cited_by_count":6,"area":null},{"id":"2106.10821","title":"Demonstration of Panda: A Weakly Supervised Entity Matching System","created":"2021-06-21","cited_by_count":6,"area":null},{"id":"2111.01657","title":"LogLAB: Attention-Based Labeling of Log Data Anomalies via Weak Supervision","created":"2021-11-02","cited_by_count":6,"area":null},{"id":"2111.15186","title":"Automatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysis","created":"2021-11-30","cited_by_count":6,"area":null},{"id":"2206.06484","title":"On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice","created":"2022-06-13","cited_by_count":6,"area":null},{"id":"2210.02724","title":"Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision","created":"2022-10-06","cited_by_count":6,"area":null},{"id":"2211.12620","title":"Promises and Pitfalls of Threshold-based Auto-labeling","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2212.10057","title":"WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2305.13723","title":"PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2311.06673","title":"Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination","created":"2023-11-11","cited_by_count":6,"area":null},{"id":"2407.01490","title":"LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2506.10403","title":"Time To Impeach LLM-as-a-Judge: Programs are the Future of Evaluation","created":"2025-06-12","cited_by_count":6,"area":null},{"id":"2202.03250","title":"Adaptive Mixing of Auxiliary Losses in Supervised Learning","created":"2022-02-07","cited_by_count":5,"area":"distill"},{"id":"2211.06975","title":"Ground Truth Inference for Weakly Supervised Entity Matching","created":"2022-11-13","cited_by_count":5,"area":null},{"id":"2306.00932","title":"Cross Modal Data Discovery over Structured and Unstructured Data Lakes","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2306.16564","title":"Pareto Optimal Learning for Estimating Large Language Model Errors","created":"2023-06-28","cited_by_count":5,"area":null},{"id":"2310.06111","title":"BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions","created":"2023-10-09","cited_by_count":5,"area":null}],"next_cursor":"100"}