{"total":34,"rows":[{"id":"2405.05860","title":"The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human Labels","created":"2024-05-09","cited_by_count":38,"area":null},{"id":"2502.20897","title":"Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions","created":"2025-02-28","cited_by_count":33,"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":"2402.14147","title":"Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia","created":"2024-02-21","cited_by_count":18,"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":"2601.09065","title":"Beyond Consensus: Perspectivist Modeling and Evaluation of Annotator Disagreement in NLP","created":"2026-01-14","cited_by_count":13,"area":null},{"id":"2603.06865","title":"Counting on Consensus: Selecting the Right Inter-annotator Agreement Metric for NLP Annotation and Evaluation","created":"2026-03-06","cited_by_count":13,"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":"2407.14259","title":"Voices in a Crowd: Searching for Clusters of Unique Perspectives","created":"2024-07-19","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":"2502.01891","title":"Training and Evaluating with Human Label Variation: An Empirical Study","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2507.18890","title":"NUTMEG: Separating Signal From Noise in Annotator Disagreement","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2409.12218","title":"ARTICLE: Annotator Reliability Through In-Context Learning","created":"2024-09-18","cited_by_count":6,"area":null},{"id":"2601.08951","title":"PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2402.14101","title":"Cost-Efficient Subjective Task Annotation and Modeling through Few-Shot Annotator Adaptation","created":"2024-02-21","cited_by_count":4,"area":null},{"id":"2412.17729","title":"Chumor 2.0: Towards Benchmarking Chinese Humor Understanding","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2406.12754","title":"Chumor 1.0: A Truly Funny and Challenging Chinese Humor Understanding Dataset from Ruo Zhi Ba","created":"2024-06-18","cited_by_count":3,"area":null},{"id":"2410.12217","title":"Accurate and Data-Efficient Toxicity Prediction when Annotators Disagree","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2411.04090","title":"A Collaborative Content Moderation Framework for Toxicity Detection based on Conformalized Estimates of Annotation Disagreement","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2509.06704","title":"Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments","created":"2025-09-08","cited_by_count":3,"area":null},{"id":"2510.04441","title":"Domain Generalization Under Posterior Drift","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2604.07591","title":"From Ground Truth to Measurement: A Statistical Framework for Human Labeling","created":"2026-04-08","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":"2404.06670","title":"What's Mine becomes Yours: Defining, Annotating and Detecting Context-Dependent Paraphrases in News Interview Dialogs","created":"2024-04-10","cited_by_count":1,"area":null},{"id":"2604.07894","title":"TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2509.14712","title":"From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2509.17794","title":"Learning to vary: Teaching LMs to reproduce human linguistic variability in next-word prediction","created":"2025-09-22","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":"2602.22723","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":"2604.16654","title":"IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.27313","title":"When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection","created":"2026-05-26","cited_by_count":0,"area":null}],"next_cursor":null}