{"total":25,"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":"2304.14399","title":"We're Afraid Language Models Aren't Modeling Ambiguity","created":"2023-04-27","cited_by_count":126,"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":"2305.14663","title":"You Are What You Annotate: Towards Better Models through Annotator Representations","created":"2023-05-24","cited_by_count":40,"area":null},{"id":"2201.06028","title":"Natural Language Deduction through Search over Statement Compositions","created":"2022-01-16","cited_by_count":35,"area":null},{"id":"2305.13788","title":"Can Large Language Models Capture Dissenting Human Voices?","created":"2023-05-23","cited_by_count":33,"area":null},{"id":"2209.03392","title":"Investigating Reasons for Disagreement in Natural Language Inference","created":"2022-09-07","cited_by_count":29,"area":null},{"id":"2305.00350","title":"POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models","created":"2023-04-29","cited_by_count":29,"area":null},{"id":"2205.04980","title":"ALLSH: Active Learning Guided by Local Sensitivity and Hardness","created":"2022-05-10","cited_by_count":23,"area":null},{"id":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","cited_by_count":19,"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":"2110.12567","title":"Alignment Attention by Matching Key and Query Distributions","created":"2021-10-25","cited_by_count":14,"area":null},{"id":"2304.00815","title":"Design Choices for Crowdsourcing Implicit Discourse Relations: Revealing the Biases Introduced by Task Design","created":"2023-04-03","cited_by_count":14,"area":null},{"id":"2305.01645","title":"Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2110.08355","title":"Clean or Annotate: How to Spend a Limited Data Collection Budget","created":"2021-10-15","cited_by_count":10,"area":null},{"id":"2404.02340","title":"Corpus Considerations for Annotator Modeling and Scaling","created":"2024-04-02","cited_by_count":8,"area":null},{"id":"2305.16337","title":"Handling Realistic Label Noise in BERT Text Classification","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2310.14572","title":"Unveiling the Multi-Annotation Process: Examining the Influence of Annotation Quantity and Instance Difficulty on Model Performance","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2302.03807","title":"A Prototype-Oriented Clustering for Domain Shift with Source Privacy","created":"2023-02-08","cited_by_count":2,"area":null},{"id":"2212.02745","title":"Sources of Noise in Dialogue and How to Deal with Them","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2306.07061","title":"Deep Model Compression Also Helps Models Capture Ambiguity","created":"2023-06-12","cited_by_count":1,"area":null},{"id":"2312.15751","title":"Solving Label Variation in Scientific Information Extraction via Multi-Task Learning","created":"2023-12-25","cited_by_count":1,"area":null},{"id":"2405.04513","title":"Switchable Decision: Dynamic Neural Generation Networks","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2511.20997","title":"FANoise: Singular Value-Adaptive Noise Modulation for Robust Multimodal Representation Learning","created":"2025-11-26","cited_by_count":0,"area":null}],"next_cursor":null}