{"total":62,"rows":[{"id":"2109.05322","title":"Latent Hatred: A Benchmark for Understanding Implicit Hate Speech","created":"2021-09-11","cited_by_count":217,"area":null},{"id":"2304.10145","title":"Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks","created":"2023-04-20","cited_by_count":89,"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":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73,"area":null},{"id":"2106.01625","title":"Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech","created":"2021-06-03","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":"2206.06423","title":"Hate Speech and Counter Speech Detection: Conversational Context Does Matter","created":"2022-06-13","cited_by_count":32,"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":"2205.04304","title":"CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech","created":"2022-05-09","cited_by_count":29,"area":null},{"id":"2401.16727","title":"Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models","created":"2024-01-30","cited_by_count":26,"area":null},{"id":"2311.00161","title":"Beyond Denouncing Hate: Strategies for Countering Implied Biases and Stereotypes in Language","created":"2023-10-31","cited_by_count":24,"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":"2404.01651","title":"NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helps","created":"2024-04-02","cited_by_count":20,"area":null},{"id":"2307.04761","title":"Understanding Counterspeech for Online Harm Mitigation","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2403.14938","title":"On Zero-Shot Counterspeech Generation by LLMs","created":"2024-03-22","cited_by_count":17,"area":null},{"id":"2311.18147","title":"DisCGen: A Framework for Discourse-Informed Counterspeech Generation","created":"2023-11-29","cited_by_count":14,"area":null},{"id":"2107.02472","title":"Empowering NGOs in Countering Online Hate Messages","created":"2021-07-06","cited_by_count":13,"area":null},{"id":"2305.13776","title":"Counterspeeches up my sleeve! Intent Distribution Learning and Persistent Fusion for Intent-Conditioned Counterspeech Generation","created":"2023-05-23","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":"2210.02659","title":"Explainable Abuse Detection as Intent Classification and Slot Filling","created":"2022-10-06","cited_by_count":11,"area":null},{"id":"2109.13664","title":"Multilingual Counter Narrative Type Classification","created":"2021-09-28","cited_by_count":10,"area":null},{"id":"2312.04804","title":"Hate Cannot Drive out Hate: Forecasting Conversation Incivility following Replies to Hate Speech","created":"2023-12-08","cited_by_count":10,"area":null},{"id":"2208.00176","title":"ELF22: A Context-based Counter Trolling Dataset to Combat Internet Trolls","created":"2022-07-30","cited_by_count":7,"area":null},{"id":"2403.09159","title":"Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation","created":"2024-03-14","cited_by_count":7,"area":null},{"id":"2102.04427","title":"RECAST: Enabling User Recourse and Interpretability of Toxicity Detection Models with Interactive Visualization","created":"2021-02-08","cited_by_count":6,"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":"2203.03584","title":"Counter Hate Speech in Social Media: A Survey","created":"2022-02-21","cited_by_count":5,"area":null},{"id":"2402.07262","title":"Low-Resource Counterspeech Generation for Indic Languages: The Case of Bengali and Hindi","created":"2024-02-11","cited_by_count":5,"area":null},{"id":"2410.01400","title":"CrowdCounter: A benchmark type-specific multi-target counterspeech dataset","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2501.16235","title":"Echoes of Discord: Forecasting Hater Reactions to Counterspeech","created":"2025-01-27","cited_by_count":5,"area":null},{"id":"2508.08274","title":"Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2409.16673","title":"SWE2: SubWord Enriched and Significant Word Emphasized Framework for Hate Speech Detection","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2501.12640","title":"Toxicity Begets Toxicity: Unraveling Conversational Chains in Political Podcasts","created":"2025-01-22","cited_by_count":4,"area":null},{"id":"2501.17581","title":"CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2601.04692","title":"PEST: Parameter Efficient Steering of Blackbox VLMs via Agentic Few-shot Alignment for Hateful Meme Moderation","created":"2026-01-08","cited_by_count":4,"area":null},{"id":"2201.06721","title":"Selecting and combining complementary feature representations and classifiers for hate speech detection","created":"2022-01-18","cited_by_count":3,"area":null},{"id":"2312.07228","title":"Toxic language detection: a systematic review of Arabic datasets","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2404.11845","title":"Challenging Negative Gender Stereotypes: A Study on the Effectiveness of Automated Counter-Stereotypes","created":"2024-04-18","cited_by_count":3,"area":null},{"id":"2411.02580","title":"Social Support Detection from Social Media Texts","created":"2024-11-04","cited_by_count":3,"area":null},{"id":"2303.16173","title":"Towards Countering Essentialism through Social Bias Reasoning","created":"2023-03-28","cited_by_count":2,"area":null},{"id":"2403.15449","title":"Hatred Stems from Ignorance! Distillation of the Persuasion Modes in Countering Conversational Hate Speech","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2406.15809","title":"LaMSUM: Amplifying Voices Against Harassment through LLM Guided Extractive Summarization of User Incident Reports","created":"2024-06-22","cited_by_count":2,"area":null},{"id":"2502.09004","title":"Hope vs. Hate: Understanding User Interactions with LGBTQ+ News Content in Mainstream US News Media through the Lens of Hope Speech","created":"2025-02-13","cited_by_count":2,"area":null},{"id":"2505.11958","title":"Counterspeech the ultimate shield! Multi-Conditioned Counterspeech Generation through Attributed Prefix Learning","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2506.11919","title":"Effectiveness of Counter-Speech against Abusive Content: A Multidimensional Annotation and Classification Study","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2406.12304","title":"COT: A Generative Approach for Hate Speech Counter-Narratives via Contrastive Optimal Transport","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2407.20274","title":"Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AI","created":"2024-07-25","cited_by_count":1,"area":null},{"id":"2507.04350","title":"HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2603.19279","title":"Multilingual Hate Speech Detection and Counterspeech Generation: A Comprehensive Survey and Practical Guide","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2605.22435","title":"Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2407.06422","title":"Exploring the Capability of ChatGPT to Reproduce Human Labels for Social Computing Tasks (Extended Version)","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2409.17191","title":"An Effective, Robust and Fairness-aware Hate Speech Detection Framework","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2410.03032","title":"Designing Human-AI Collaboration to Support Learning in Counterspeech Writing","created":"2024-10-03","cited_by_count":0,"area":null},{"id":"2507.20528","title":"Dialogues of Dissent: Thematic and Rhetorical Dimensions of Hate and Counter-Hate Speech in Social Media Conversations","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2508.15855","title":"Counterspeech for Mitigating the Influence of Media Bias: Comparing Human and LLM-Generated Responses","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2512.00673","title":"A Comparison of Human and ChatGPT Classification Performance on Complex Social Media Data","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2512.14700","title":"Context-Aware Detection and Victim-Centered Response Generation for Online Harassment in Private Messaging","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2602.17467","title":"PEACE 2.0: Grounded Explanations and Counter-Speech for Combating Hate Expressions","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2606.20369","title":"CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.23152","title":"Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.16906","title":"Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeech","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}