{"total":44,"rows":[{"id":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139,"area":null},{"id":"2306.04140","title":"Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions","created":"2023-06-07","cited_by_count":125,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2402.15052","title":"ToMBench: Benchmarking Theory of Mind in Large Language Models","created":"2024-02-23","cited_by_count":72,"area":null},{"id":"2210.16133","title":"Stop Measuring Calibration When Humans Disagree","created":"2022-10-28","cited_by_count":71,"area":null},{"id":"2403.01931","title":"VariErr NLI: Separating Annotation Error from Human Label Variation","created":"2024-03-04","cited_by_count":42,"area":null},{"id":"2307.08153","title":"Analyzing Dataset Annotation Quality Management in the Wild","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2511.02817","title":"Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities","created":"2025-11-04","cited_by_count":40,"area":null},{"id":"2305.08414","title":"What's the Meaning of Superhuman Performance in Today's NLU?","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2410.18889","title":"Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance","created":"2024-10-24","cited_by_count":20,"area":null},{"id":"2402.16102","title":"Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?","created":"2024-02-25","cited_by_count":15,"area":null},{"id":"2207.13211","title":"A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialog","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2405.20900","title":"Large Language Models: A New Approach for Privacy Policy Analysis at Scale","created":"2024-05-31","cited_by_count":14,"area":null},{"id":"2210.03920","title":"Detecting Label Errors in Token Classification Data","created":"2022-10-08","cited_by_count":12,"area":null},{"id":"2211.13895","title":"Identifying Incorrect Annotations in Multi-Label Classification Data","created":"2022-11-25","cited_by_count":12,"area":null},{"id":"2307.05080","title":"Estimating label quality and errors in semantic segmentation data via any model","created":"2023-07-11","cited_by_count":12,"area":null},{"id":"2309.00832","title":"ObjectLab: Automated Diagnosis of Mislabeled Images in Object Detection Data","created":"2023-09-02","cited_by_count":11,"area":null},{"id":"2305.20045","title":"ActiveAED: A Human in the Loop Improves Annotation Error Detection","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2310.01765","title":"Data Cleaning and Machine Learning: A Systematic Literature Review","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2406.04461","title":"Multi-Label Classification for Implicit Discourse Relation Recognition","created":"2024-06-06","cited_by_count":9,"area":null},{"id":"2502.20480","title":"VideoA11y: Method and Dataset for Accessible Video Description","created":"2025-02-27","cited_by_count":9,"area":null},{"id":"2405.11919","title":"On Efficient and Statistical Quality Estimation for Data Annotation","created":"2024-05-20","cited_by_count":8,"area":null},{"id":"2408.03325","title":"CoverBench: A Challenging Benchmark for Complex Claim Verification","created":"2024-08-06","cited_by_count":6,"area":null},{"id":"2402.01423","title":"Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2509.04304","title":"Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2406.14099","title":"Let Guidelines Guide You: A Prescriptive Guideline-Centered Data Annotation Methodology","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2605.30504","title":"Auditing LLM Benchmarks with Item Response Theory","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2308.08825","title":"Controlling Federated Learning for Covertness","created":"2023-08-17","cited_by_count":2,"area":null},{"id":"2311.16481","title":"Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learning","created":"2023-11-25","cited_by_count":2,"area":null},{"id":"2601.02285","title":"pdfQA: Diverse, Challenging, and Realistic Question Answering over PDFs","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2309.01669","title":"Donkii: Can Annotation Error Detection Methods Find Errors in Instruction-Tuning Datasets?","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2405.07609","title":"NoiseBench: Benchmarking the Impact of Real Label Noise on Named Entity Recognition","created":"2024-05-13","cited_by_count":1,"area":null},{"id":"2408.13738","title":"Poor-Supervised Evaluation for SuperLLM via Mutual Consistency","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2601.11920","title":"Enhancing LLM-Based Data Annotation with Error Decomposition","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2603.21174","title":"Explainable Semantic Textual Similarity via Dissimilar Span Detection","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2210.16458","title":"Reformulating van Rijsbergen's $F_{\\beta}$ metric for weighted binary cross-entropy","created":"2022-10-29","cited_by_count":0,"area":null},{"id":"2310.05286","title":"Generalizable Error Modeling for Human Data Annotation: Evidence From an Industry-Scale Search Data Annotation Program","created":"2023-10-08","cited_by_count":0,"area":null},{"id":"2409.04041","title":"On Evaluation of Vision Datasets and Models using Human Competency Frameworks","created":"2024-09-06","cited_by_count":0,"area":null},{"id":"2512.10821","title":"Agile Deliberation: Concept Deliberation for Subjective Visual Classification","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2601.16753","title":"Standardizing Longitudinal Radiology Report Evaluation via Large Language Model Annotation","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2602.15298","title":"X-MAP: eXplainable Misclassification Analysis and Profiling for Spam and Phishing Detection","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2602.22723","title":"Human Label Variation in Implicit Discourse Relation Recognition","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.00114","title":"Automated Quality Check of Sensor Data Annotations","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2609.17554","title":"English Word Sense Disambiguation in 2026: When the Labels Become the Bottleneck","created":"2026-07-19","cited_by_count":0,"area":null}],"next_cursor":null}