{"total":66,"rows":[{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422,"area":null},{"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":"2304.14803","title":"SemEval-2023 Task 11: Learning With Disagreements (LeWiDi)","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2306.06826","title":"When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset","created":"2023-06-12","cited_by_count":52,"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":"2311.09743","title":"Capturing Perspectives of Crowdsourced Annotators in Subjective Learning Tasks","created":"2023-11-16","cited_by_count":29,"area":null},{"id":"2405.01299","title":"The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation","created":"2024-05-02","cited_by_count":29,"area":null},{"id":"2111.02110","title":"Automatic Evaluation and Moderation of Open-domain Dialogue Systems","created":"2021-11-03","cited_by_count":28,"area":null},{"id":"2301.10684","title":"Consistency is Key: Disentangling Label Variation in Natural Language Processing with Intra-Annotator Agreement","created":"2023-01-25","cited_by_count":23,"area":null},{"id":"2210.14531","title":"Unifying Data Perspectivism and Personalization: An Application to Social Norms","created":"2022-10-26","cited_by_count":22,"area":null},{"id":"2404.15720","title":"Annotator-Centric Active Learning for Subjective NLP Tasks","created":"2024-04-24","cited_by_count":18,"area":null},{"id":"2301.12534","title":"Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive","created":"2023-01-29","cited_by_count":16,"area":null},{"id":"2502.06207","title":"Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2408.14141","title":"Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?","created":"2024-08-26","cited_by_count":13,"area":null},{"id":"2112.07475","title":"Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks","created":"2021-12-14","cited_by_count":12,"area":null},{"id":"2404.10857","title":"D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation","created":"2024-04-16","cited_by_count":11,"area":null},{"id":"2305.06074","title":"iLab at SemEval-2023 Task 11 Le-Wi-Di: Modelling Disagreement or Modelling Perspectives?","created":"2023-05-10","cited_by_count":10,"area":null},{"id":"2403.04085","title":"Don't Blame the Data, Blame the Model: Understanding Noise and Bias When Learning from Subjective Annotations","created":"2024-03-06","cited_by_count":10,"area":null},{"id":"2403.02268","title":"Subjective $\\textit{Isms}$? On the Danger of Conflating Hate and Offence in Abusive Language Detection","created":"2024-03-04","cited_by_count":9,"area":null},{"id":"2510.08460","title":"LeWiDi-2025 at NLPerspectives: Third Edition of the Learning with Disagreements Shared Task","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2404.02340","title":"Corpus Considerations for Annotator Modeling and Scaling","created":"2024-04-02","cited_by_count":8,"area":null},{"id":"2410.03543","title":"Re-examining Sexism and Misogyny Classification with Annotator Attitudes","created":"2024-10-04","cited_by_count":8,"area":null},{"id":"2502.01891","title":"Training and Evaluating with Human Label Variation: An Empirical Study","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2311.00203","title":"Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2409.12218","title":"ARTICLE: Annotator Reliability Through In-Context Learning","created":"2024-09-18","cited_by_count":6,"area":null},{"id":"2112.02265","title":"\"Stop Asian Hate!\" : Refining Detection of Anti-Asian Hate Speech During the COVID-19 Pandemic","created":"2021-12-04","cited_by_count":4,"area":null},{"id":"2208.08758","title":"Understanding Interpersonal Conflict Types and their Impact on Perception Classification","created":"2022-08-18","cited_by_count":4,"area":null},{"id":"2210.07595","title":"The State of Profanity Obfuscation in Natural Language Processing","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2211.06053","title":"CoRAL: a Context-aware Croatian Abusive Language Dataset","created":"2022-11-11","cited_by_count":4,"area":null},{"id":"2309.14146","title":"Examining Temporal Bias in Abusive Language Detection","created":"2023-09-25","cited_by_count":4,"area":null},{"id":"2402.13528","title":"Infrastructure Ombudsman: Mining Future Failure Concerns from Structural Disaster Response","created":"2024-02-21","cited_by_count":4,"area":null},{"id":"2411.10080","title":"Understanding The Effect Of Temperature On Alignment With Human Opinions","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2507.13138","title":"Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation","created":"2025-07-17","cited_by_count":4,"area":null},{"id":"2212.02108","title":"Human-in-the-Loop Hate Speech Classification in a Multilingual Context","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2404.04035","title":"A Dataset for Physical and Abstract Plausibility and Sources of Human Disagreement","created":"2024-04-05","cited_by_count":3,"area":null},{"id":"2410.16520","title":"AUTALIC: A Dataset for Anti-AUTistic Ableist Language In Context","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2503.11381","title":"Modeling Subjectivity in Cognitive Appraisal with Language Models","created":"2025-03-14","cited_by_count":3,"area":null},{"id":"2306.04925","title":"Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2311.00619","title":"Noise Correction on Subjective Datasets","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2311.03584","title":"Dimensions of Online Conflict: Towards Modeling Agonism","created":"2023-11-06","cited_by_count":2,"area":null},{"id":"2406.06407","title":"A Taxonomy of Challenges to Curating Fair Datasets","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2412.02968","title":"How Many Ratings per Item are Necessary for Reliable Significance Testing?","created":"2024-12-04","cited_by_count":2,"area":null},{"id":"2502.09004","title":"Hope vs. Hate: Understanding User Interactions with LGBTQ+ News Content in Mainstream US News Media through the Lens of Hope Speech","created":"2025-02-13","cited_by_count":2,"area":null},{"id":"2605.10415","title":"Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2303.02468","title":"Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction","created":"2023-03-04","cited_by_count":1,"area":null},{"id":"2305.01050","title":"SafeWebUH at SemEval-2023 Task 11: Learning Annotator Disagreement in Derogatory Text: Comparison of Direct Training vs Aggregation","created":"2023-05-01","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":"2410.05496","title":"Intuitions of Compromise: Utilitarianism vs. Contractualism","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2510.10415","title":"CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints","created":"2025-10-12","cited_by_count":1,"area":null},{"id":"2510.17548","title":"When Annotators Disagree, Topology Explains: Mapper, a Topological Tool for Exploring Text Embedding Geometry and Ambiguity","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2512.09662","title":"Can LLMs Evaluate What They Cannot Annotate? Revisiting LLM Reliability in Hate Speech Detection","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2604.25580","title":"Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2608.17183","title":"Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2212.10152","title":"Quirk or Palmer: A Comparative Study of Modal Verb Frameworks with Annotated Datasets","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2403.13272","title":"Community Needs and Assets: A Computational Analysis of Community Conversations","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2510.13259","title":"Hypernetworks for Perspectivist Adaptation","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2512.16034","title":"Examining the Utility of Self-disclosure Types for Modeling Annotators of Social Norms","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2602.15866","title":"NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey","created":"2026-01-26","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":"2603.28351","title":"Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.08425","title":"Learning Who Disagrees: Demographic Importance Weighting for Modeling Annotator Distributions with DiADEM","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.05329","title":"Understanding Annotator Safety Policy with Interpretability","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.09483","title":"A Cognitively Grounded Bayesian Framework for Misinformation Susceptibility","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.02911","title":"The Ghost Annotator: a Framework to Explore Human Label Variation in Content Moderation through Conformal Prediction","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.08493","title":"Ensemble Diversity Optimization for Subjective Supervision","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.15619","title":"Bias-Corrected Ceilings of Emotion Predictability from Human Label Variation Based on Instance-Level Fano Bounds","created":"2026-08-16","cited_by_count":0,"area":null}],"next_cursor":null}