{"total":39,"rows":[{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202,"area":null},{"id":"2107.08720","title":"Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech","created":"2021-07-19","cited_by_count":82,"area":null},{"id":"2108.03070","title":"SWSR: A Chinese Dataset and Lexicon for Online Sexism Detection","created":"2021-08-06","cited_by_count":42,"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":"2108.01250","title":"Your fairness may vary: Pretrained language model fairness in toxic text classification","created":"2021-08-03","cited_by_count":39,"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":"2406.18841","title":"Navigating LLM Ethics: Advancements, Challenges, and Future Directions","created":"2024-05-14","cited_by_count":28,"area":null},{"id":"2312.06861","title":"Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates","created":"2023-12-11","cited_by_count":26,"area":null},{"id":"2403.20103","title":"NLP for Counterspeech against Hate: A Survey and How-To Guide","created":"2024-03-29","cited_by_count":22,"area":null},{"id":"2205.03302","title":"Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection","created":"2022-05-06","cited_by_count":18,"area":null},{"id":"2206.15455","title":"Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions","created":"2022-06-30","cited_by_count":18,"area":null},{"id":"2110.05111","title":"Dynamic Forecasting of Conversation Derailment","created":"2021-10-11","cited_by_count":16,"area":null},{"id":"2204.02261","title":"Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors","created":"2022-04-05","cited_by_count":14,"area":null},{"id":"2210.09306","title":"Mitigating Covertly Unsafe Text within Natural Language Systems","created":"2022-10-17","cited_by_count":13,"area":null},{"id":"2109.02941","title":"Countering Online Hate Speech: An NLP Perspective","created":"2021-09-07","cited_by_count":12,"area":null},{"id":"2110.14839","title":"Hate Speech Classifiers Learn Human-Like Social Stereotypes","created":"2021-10-28","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":"2410.03884","title":"KidLM: Advancing Language Models for Children -- Early Insights and Future Directions","created":"2024-10-04","cited_by_count":8,"area":null},{"id":"2212.09667","title":"Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AI","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2211.13709","title":"Undesirable Biases in NLP: Addressing Challenges of Measurement","created":"2022-11-24","cited_by_count":4,"area":null},{"id":"2303.14128","title":"The crime of being poor","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2401.15535","title":"Quantifying Stereotypes in Language","created":"2024-01-28","cited_by_count":4,"area":null},{"id":"2404.12042","title":"Exploring Boundaries and Intensities in Offensive and Hate Speech: Unveiling the Complex Spectrum of Social Media Discourse","created":"2024-04-18","cited_by_count":4,"area":null},{"id":"2212.14100","title":"Leveraging World Knowledge in Implicit Hate Speech Detection","created":"2022-12-28","cited_by_count":3,"area":null},{"id":"2402.15238","title":"GPT-HateCheck: Can LLMs Write Better Functional Tests for Hate Speech Detection?","created":"2024-02-23","cited_by_count":3,"area":null},{"id":"2509.25539","title":"Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2303.00908","title":"Interactive Text Generation","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2401.07810","title":"Consolidating Strategies for Countering Hate Speech Using Persuasive Dialogues","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2401.09244","title":"Cross-lingual Offensive Language Detection: A Systematic Review of Datasets, Transfer Approaches and Challenges","created":"2024-01-17","cited_by_count":2,"area":null},{"id":"2506.04693","title":"Cracking the Code: Enhancing Implicit Hate Speech Detection through Coding Classification","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2507.19470","title":"Conversations Gone Awry, But Then? Evaluating Conversational Forecasting Models","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2306.12982","title":"Conversation Derailment Forecasting with Graph Convolutional Networks","created":"2023-06-22","cited_by_count":1,"area":null},{"id":"2210.04756","title":"Metaphorical Paraphrase Generation: Feeding Metaphorical Language Models with Literal Texts","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2304.13568","title":"Toxic comments reduce the activity of volunteer editors on Wikipedia","created":"2023-04-26","cited_by_count":0,"area":null},{"id":"2408.13440","title":"Knowledge-Aware Conversation Derailment Forecasting Using Graph Convolutional Networks","created":"2024-08-24","cited_by_count":0,"area":null},{"id":"2503.16072","title":"Toxicity Is a Property of Communicative Events: A Contextual Stress Measurement Framework for NLP","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2504.13085","title":"Tackling Social Bias against the Poor: A Dataset and Taxonomy on Aporophobia","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2504.13231","title":"WildFireCan-MMD: A Multimodal Dataset for Classification of User-Generated Content During Wildfires in Canada","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2605.27584","title":"Cyberbullying Governance on Social Media: A Unified Framework from Content Identification to Intervention","created":"2026-05-26","cited_by_count":0,"area":null}],"next_cursor":null}