{"total":33,"rows":[{"id":"2205.00501","title":"Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation","created":"2022-05-01","cited_by_count":69,"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":"2308.16705","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","created":"2023-08-31","cited_by_count":45,"area":null},{"id":"2304.12397","title":"On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research","created":"2023-04-24","cited_by_count":44,"area":null},{"id":"2211.03433","title":"Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering","created":"2022-11-07","cited_by_count":40,"area":null},{"id":"2204.01440","title":"Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study","created":"2022-04-04","cited_by_count":30,"area":null},{"id":"2102.04256","title":"Problematic Machine Behavior: A Systematic Literature Review of Algorithm Audits","created":"2021-02-03","cited_by_count":21,"area":null},{"id":"2110.04419","title":"Detecting Community Sensitive Norm Violations in Online Conversations","created":"2021-10-09","cited_by_count":18,"area":null},{"id":"2306.06135","title":"Safety and Fairness for Content Moderation in Generative Models","created":"2023-06-09","cited_by_count":16,"area":null},{"id":"2310.20470","title":"Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation","created":"2023-10-31","cited_by_count":16,"area":null},{"id":"2203.07031","title":"Model Positionality and Computational Reflexivity: Promoting Reflexivity in Data Science","created":"2022-03-08","cited_by_count":13,"area":null},{"id":"2503.01623","title":"Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2212.10405","title":"AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detection","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2111.03299","title":"Dataset of Fake News Detection and Fact Verification: A Survey","created":"2021-11-05","cited_by_count":11,"area":null},{"id":"2106.02183","title":"Towards Equal Gender Representation in the Annotations of Toxic Language Detection","created":"2021-06-04","cited_by_count":9,"area":null},{"id":"2206.11484","title":"Towards WinoQueer: Developing a Benchmark for Anti-Queer Bias in Large Language Models","created":"2022-06-23","cited_by_count":8,"area":null},{"id":"2408.08411","title":"Rater Cohesion and Quality from a Vicarious Perspective","created":"2024-08-15","cited_by_count":8,"area":null},{"id":"2211.11798","title":"Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions","created":"2022-11-21","cited_by_count":7,"area":null},{"id":"2307.10189","title":"Subjective Crowd Disagreements for Subjective Data: Uncovering Meaningful CrowdOpinion with Population-level Learning","created":"2023-07-07","cited_by_count":7,"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":"2108.12601","title":"Mitigation of Diachronic Bias in Fake News Detection Dataset","created":"2021-08-28","cited_by_count":5,"area":null},{"id":"2406.18865","title":"From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions","created":"2024-06-27","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":"2409.13725","title":"Identity-related Speech Suppression in Generative AI Content Moderation","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2411.13760","title":"A Framework for Evaluating LLMs Under Task Indeterminacy","created":"2024-11-21","cited_by_count":3,"area":null},{"id":"2108.13892","title":"Like Article, Like Audience: Enforcing Multimodal Correlations for Disinformation Detection","created":"2021-08-31","cited_by_count":2,"area":null},{"id":"2210.09014","title":"Addressing contingency in algorithmic (mis)information classification: Toward a responsible machine learning agenda","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2305.14735","title":"Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2203.11401","title":"Suum Cuique: Studying Bias in Taboo Detection with a Community Perspective","created":"2022-03-22","cited_by_count":0,"area":null},{"id":"2311.09367","title":"A Survey on Online User Aggression: Content Detection and Behavioral Analysis on Social Media","created":"2023-11-15","cited_by_count":0,"area":null},{"id":"2508.07872","title":"Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2602.06055","title":"Are we chasing ghosts? Quantifying unattributable polarization, and attributing the rest to annotator groups","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2605.17187","title":"PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media","created":"2026-05-16","cited_by_count":0,"area":null}],"next_cursor":null}