{"total":41,"rows":[{"id":"2310.17389","title":"ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation","created":"2023-10-26","cited_by_count":231,"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":"2306.11559","title":"The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics","created":"2023-06-20","cited_by_count":46,"area":null},{"id":"2305.09800","title":"Mirages: On Anthropomorphism in Dialogue Systems","created":"2023-05-16","cited_by_count":30,"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":"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":"2203.10012","title":"Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges","created":"2022-03-18","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":"2210.00572","title":"Risk-graded Safety for Handling Medical Queries in Conversational AI","created":"2022-10-02","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":"2402.15951","title":"DetoxLLM: A Framework for Detoxification with Explanations","created":"2024-02-25","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":"2409.17577","title":"Leveraging Annotator Disagreement for Text Classification","created":"2024-09-26","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":"2410.00775","title":"Decoding Hate: Exploring Language Models' Reactions to Hate Speech","created":"2024-10-01","cited_by_count":6,"area":null},{"id":"2311.03153","title":"Architectural Sweet Spots for Modeling Human Label Variation by the Example of Argument Quality: It's Best to Relate Perspectives!","created":"2023-11-06","cited_by_count":5,"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":"2410.17032","title":"Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups","created":"2024-10-22","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":"2506.20209","title":"Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2308.12648","title":"From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue","created":"2023-08-24","cited_by_count":3,"area":null},{"id":"2508.17164","title":"The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum","created":"2025-08-23","cited_by_count":3,"area":null},{"id":"2605.02122","title":"STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems","created":"2026-05-04","cited_by_count":3,"area":null},{"id":"2212.00851","title":"SOLD: Sinhala Offensive Language Dataset","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2307.16609","title":"Noisy Self-Training with Data Augmentations for Offensive and Hate Speech Detection Tasks","created":"2023-07-31","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":"2211.06452","title":"Cross-Platform and Cross-Domain Abusive Language Detection with Supervised Contrastive Learning","created":"2022-11-11","cited_by_count":1,"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":"2403.03874","title":"Impoverished Language Technology: The Lack of (Social) Class in NLP","created":"2024-03-06","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":"2502.12225","title":"Subjective Logic Encodings","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2309.02912","title":"On the Challenges of Building Datasets for Hate Speech Detection","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2312.13193","title":"HCDIR: End-to-end Hate Context Detection, and Intensity Reduction model for online comments","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2504.17653","title":"Towards a comprehensive taxonomy of online abusive language informed by machine leaning","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2506.16190","title":"Web(er) of Hate: A Survey on How Hate Speech Is Typed","created":"2025-06-19","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":"2609.17547","title":"How AI Assistants Respond to Repeated Abuse","created":"2026-07-15","cited_by_count":0,"area":null}],"next_cursor":null}