{"total":34,"rows":[{"id":"2401.17633","title":"Navigating the OverKill in Large Language Models","created":"2024-01-31","cited_by_count":44,"area":null},{"id":"2302.00871","title":"Using In-Context Learning to Improve Dialogue Safety","created":"2023-02-02","cited_by_count":42,"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":"2311.18147","title":"DisCGen: A Framework for Discourse-Informed Counterspeech Generation","created":"2023-11-29","cited_by_count":14,"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":"2403.17146","title":"Outcome-Constrained Large Language Models for Countering Hate Speech","created":"2024-03-25","cited_by_count":12,"area":null},{"id":"2309.02311","title":"Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization","created":"2023-09-05","cited_by_count":7,"area":null},{"id":"2305.15908","title":"Response Generation in Longitudinal Dialogues: Which Knowledge Representation Helps?","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2402.11676","title":"A Multi-Aspect Framework for Counter Narrative Evaluation using Large Language Models","created":"2024-02-18","cited_by_count":6,"area":null},{"id":"2406.15227","title":"A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation","created":"2024-06-21","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":"2307.07047","title":"Does Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues?","created":"2023-07-13","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":"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":"2401.07810","title":"Consolidating Strategies for Countering Hate Speech Using Persuasive Dialogues","created":"2024-01-15","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":"2504.16604","title":"Debunking with Dialogue? Exploring AI-Generated Counterspeech to Challenge Conspiracy Theories","created":"2025-04-23","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":"2604.11427","title":"METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2401.14616","title":"Alternative Speech: Complementary Method to Counter-Narrative for Better Discourse","created":"2024-01-26","cited_by_count":1,"area":null},{"id":"2404.00207","title":"Causal Inference for Human-Language Model Collaboration","created":"2024-03-30","cited_by_count":1,"area":null},{"id":"2507.20264","title":"EMBRACE: Shaping Inclusive Opinion Representation by Aligning Implicit Conversations with Social Norms","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2304.01179","title":"Hate Speech Targets Detection in Parler using BERT","created":"2023-04-03","cited_by_count":0,"area":null},{"id":"2309.00751","title":"Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence","created":"2023-09-01","cited_by_count":0,"area":null},{"id":"2404.08666","title":"Revealing Trends in Datasets from the 2022 ACL and EMNLP Conferences","created":"2024-03-31","cited_by_count":0,"area":null},{"id":"2508.04638","title":"Can NLP Tackle Hate Speech in the Real World? Stakeholder-Informed Feedback and Survey on Counterspeech","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2511.07405","title":"SPOT: An Annotated French Corpus and Benchmark for Detecting Critical Interventions in Online Conversations","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2601.01350","title":"FC-CONAN: An Exhaustively Paired Dataset for Robust Evaluation of Retrieval Systems","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2601.04135","title":"LLMberjack: Guided Trimming of Debate Trees for Multi-Party Conversation Creation","created":"2026-01-07","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":"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}