{"total":47,"rows":[{"id":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314,"area":null},{"id":"2109.05322","title":"Latent Hatred: A Benchmark for Understanding Implicit Hate Speech","created":"2021-09-11","cited_by_count":217,"area":null},{"id":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78,"area":null},{"id":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75,"area":null},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2106.15896","title":"Whose Opinions Matter? Perspective-aware Models to Identify Opinions of Hate Speech Victims in Abusive Language Detection","created":"2021-06-30","cited_by_count":38,"area":null},{"id":"2306.01985","title":"COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements","created":"2023-06-03","cited_by_count":34,"area":null},{"id":"2311.00321","title":"HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning","created":"2023-11-01","cited_by_count":31,"area":null},{"id":"2410.13155","title":"SLM-Mod: Small Language Models Surpass LLMs at Content Moderation","created":"2024-10-17","cited_by_count":27,"area":null},{"id":"2210.10839","title":"How Hate Speech Varies by Target Identity: A Computational Analysis","created":"2022-10-19","cited_by_count":23,"area":null},{"id":"2102.08368","title":"Conversations Gone Alright: Quantifying and Predicting Prosocial Outcomes in Online Conversations","created":"2021-02-16","cited_by_count":20,"area":null},{"id":"2210.02667","title":"A Human Rights-Based Approach to Responsible AI","created":"2022-10-06","cited_by_count":20,"area":null},{"id":"2103.14916","title":"Abuse is Contextual, What about NLP? The Role of Context in Abusive Language Annotation and Detection","created":"2021-03-27","cited_by_count":19,"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":"2211.16525","title":"Proactive Moderation of Online Discussions: Existing Practices and the Potential for Algorithmic Support","created":"2022-11-29","cited_by_count":15,"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":"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":"2303.03387","title":"CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network","created":"2023-03-02","cited_by_count":12,"area":null},{"id":"2205.04238","title":"Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection","created":"2022-05-09","cited_by_count":11,"area":null},{"id":"2402.15951","title":"DetoxLLM: A Framework for Detoxification with Explanations","created":"2024-02-25","cited_by_count":10,"area":null},{"id":"2106.09775","title":"An Information Retrieval Approach to Building Datasets for Hate Speech Detection","created":"2021-06-17","cited_by_count":9,"area":null},{"id":"2111.12447","title":"Revisiting Contextual Toxicity Detection in Conversations","created":"2021-11-24","cited_by_count":8,"area":null},{"id":"2205.07233","title":"Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy","created":"2022-05-15","cited_by_count":8,"area":null},{"id":"2305.09846","title":"CPL-NoViD: Context-Aware Prompt-based Learning for Norm Violation Detection in Online Communities","created":"2023-05-16","cited_by_count":7,"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":"2106.03952","title":"Predicting Different Types of Subtle Toxicity in Unhealthy Online Conversations","created":"2021-06-07","cited_by_count":5,"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":"2310.15439","title":"K-HATERS: A Hate Speech Detection Corpus in Korean with Target-Specific Ratings","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2102.04895","title":"Leveraging cross-platform data to improve automated hate speech detection","created":"2021-02-09","cited_by_count":4,"area":null},{"id":"2103.17191","title":"Modeling Users and Online Communities for Abuse Detection: A Position on Ethics and Explainability","created":"2021-03-31","cited_by_count":4,"area":null},{"id":"2111.10390","title":"The ComMA Dataset V0.2: Annotating Aggression and Bias in Multilingual Social Media Discourse","created":"2021-11-19","cited_by_count":4,"area":null},{"id":"2103.17055","title":"A Neighbourhood Framework for Resource-Lean Content Flagging","created":"2021-03-31","cited_by_count":3,"area":null},{"id":"2305.10731","title":"Analyzing Norm Violations in Live-Stream Chat","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2409.01087","title":"Pre-Trained Language Models for Keyphrase Prediction: A Review","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2112.00819","title":"CO-STAR: Conceptualisation of Stereotypes for Analysis and Reasoning","created":"2021-12-01","cited_by_count":2,"area":null},{"id":"2205.08814","title":"Exploiting Social Media Content for Self-Supervised Style Transfer","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2308.15906","title":"Is the U.S. Legal System Ready for AI's Challenges to Human Values?","created":"2023-08-30","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":"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":"2403.11108","title":"HarmPot: An Annotation Framework for Evaluating Offline Harm Potential of Social Media Text","created":"2024-03-17","cited_by_count":1,"area":null},{"id":"2508.20750","title":"Specializing General-purpose LLM Embeddings for Implicit Hate Speech Detection across Datasets","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2110.00116","title":"#ContextMatters: Advantages and Limitations of Using Machine Learning to Support Women in Politics","created":"2021-09-30","cited_by_count":0,"area":null},{"id":"2204.13400","title":"Placing M-Phasis on the Plurality of Hate: A Feature-Based Corpus of Hate Online","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2412.10939","title":"Human-Centric NLP or AI-Centric Illusion?: A Critical Investigation","created":"2024-12-14","cited_by_count":0,"area":null},{"id":"2504.12082","title":"Selective Demonstration Retrieval for Improved Implicit Hate Speech Detection","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2605.29243","title":"Wait! There's a Way Out: A Decision Mechanism for Forecasting Conversational Derailment","created":"2026-05-28","cited_by_count":0,"area":null}],"next_cursor":null}