{"total":133,"rows":[{"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":"2108.11830","title":"Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts","created":"2021-08-26","cited_by_count":56,"area":null},{"id":"2203.09192","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","created":"2022-03-17","cited_by_count":55,"area":null},{"id":"2206.09917","title":"Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models","created":"2022-06-20","cited_by_count":51,"area":null},{"id":"2402.10946","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","created":"2024-02-09","cited_by_count":50,"area":null},{"id":"2109.09483","title":"ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI","created":"2021-09-20","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":"2106.00853","title":"Claim Matching Beyond English to Scale Global Fact-Checking","created":"2021-06-01","cited_by_count":42,"area":null},{"id":"2203.01111","title":"Large-Scale Hate Speech Detection with Cross-Domain Transfer","created":"2022-03-02","cited_by_count":41,"area":null},{"id":"2205.12390","title":"Toxicity Detection with Generative Prompt-based Inference","created":"2022-05-24","cited_by_count":35,"area":null},{"id":"2103.00153","title":"Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Go","created":"2021-02-27","cited_by_count":33,"area":null},{"id":"2407.12824","title":"Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models","created":"2024-07-02","cited_by_count":32,"area":null},{"id":"2409.14703","title":"MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification","created":"2024-09-23","cited_by_count":30,"area":null},{"id":"2307.01680","title":"Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation","created":"2023-07-04","cited_by_count":28,"area":null},{"id":"2106.00742","title":"A systematic review of Hate Speech automatic detection using Natural Language Processing","created":"2021-05-22","cited_by_count":27,"area":null},{"id":"2404.17874","title":"From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets","created":"2024-04-27","cited_by_count":25,"area":null},{"id":"2410.02657","title":"Hate Personified: Investigating the role of LLMs in content moderation","created":"2024-10-03","cited_by_count":25,"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":"2203.11764","title":"Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments","created":"2022-03-22","cited_by_count":22,"area":null},{"id":"2210.03479","title":"Hate Speech and Offensive Language Detection in Bengali","created":"2022-10-07","cited_by_count":19,"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":"2310.11748","title":"BanglaAbuseMeme: A Dataset for Bengali Abusive Meme Classification","created":"2023-10-18","cited_by_count":18,"area":null},{"id":"2103.14972","title":"HateBR: A Large Expert Annotated Corpus of Brazilian Instagram Comments for Offensive Language and Hate Speech Detection","created":"2021-03-27","cited_by_count":15,"area":null},{"id":"2201.06723","title":"Emojis as Anchors to Detect Arabic Offensive Language and Hate Speech","created":"2022-01-18","cited_by_count":14,"area":null},{"id":"2205.11315","title":"KOLD: Korean Offensive Language Dataset","created":"2022-05-23","cited_by_count":14,"area":null},{"id":"2301.11219","title":"Characterizing the Entities in Harmful Memes: Who is the Hero, the Villain, the Victim?","created":"2023-01-26","cited_by_count":14,"area":null},{"id":"2401.06526","title":"MetaHate: A Dataset for Unifying Efforts on Hate Speech Detection","created":"2024-01-12","cited_by_count":14,"area":null},{"id":"2102.03870","title":"\"Short is the Road that Leads from Fear to Hate\": Fear Speech in Indian WhatsApp Groups","created":"2021-02-07","cited_by_count":13,"area":null},{"id":"2208.10684","title":"K-MHaS: A Multi-label Hate Speech Detection Dataset in Korean Online News Comment","created":"2022-08-23","cited_by_count":13,"area":null},{"id":"2211.15262","title":"HERDPhobia: A Dataset for Hate Speech against Fulani in Nigeria","created":"2022-11-28","cited_by_count":12,"area":null},{"id":"2202.07991","title":"ADIMA: Abuse Detection In Multilingual Audio","created":"2022-02-16","cited_by_count":11,"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":"2501.08284","title":"AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages","created":"2025-01-14","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":"2405.01842","title":"SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore","created":"2024-05-03","cited_by_count":10,"area":null},{"id":"2410.13281","title":"BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla","created":"2024-10-17","cited_by_count":10,"area":null},{"id":"2411.17123","title":"Advancing Content Moderation: Evaluating Large Language Models for Detecting Sensitive Content Across Text, Images, and Videos","created":"2024-11-26","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":"2310.14757","title":"SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research","created":"2023-10-23","cited_by_count":9,"area":null},{"id":"2403.13737","title":"EthioLLM: Multilingual Large Language Models for Ethiopian Languages with Task Evaluation","created":"2024-03-20","cited_by_count":8,"area":null},{"id":"2210.11359","title":"Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages","created":"2022-10-20","cited_by_count":7,"area":null},{"id":"2307.12418","title":"HateModerate: Testing Hate Speech Detectors against Content Moderation Policies","created":"2023-07-23","cited_by_count":7,"area":null},{"id":"2406.00046","title":"Hate Speech Detection with Generalizable Target-aware Fairness","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2406.04106","title":"Explainability and Hate Speech: Structured Explanations Make Social Media Moderators Faster","created":"2024-06-06","cited_by_count":7,"area":null},{"id":"2505.06149","title":"Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study","created":"2025-05-09","cited_by_count":7,"area":null},{"id":"2103.05345","title":"Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2305.13276","title":"Evaluating ChatGPT's Performance for Multilingual and Emoji-based Hate Speech Detection","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2405.08562","title":"The Unseen Targets of Hate -- A Systematic Review of Hateful Communication Datasets","created":"2024-05-14","cited_by_count":6,"area":null},{"id":"2503.15003","title":"LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones?","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2108.03089","title":"Cross-lingual Capsule Network for Hate Speech Detection in Social Media","created":"2021-08-06","cited_by_count":5,"area":null},{"id":"2303.10311","title":"On the rise of fear speech in online social media","created":"2023-03-18","cited_by_count":5,"area":null},{"id":"2506.03484","title":"Explainable AI: XAI-Guided Context-Aware Data Augmentation","created":"2025-06-04","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":"2106.07505","title":"Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces","created":"2021-06-14","cited_by_count":4,"area":null},{"id":"2108.12521","title":"TweetBLM: A Hate Speech Dataset and Analysis of Black Lives Matter-related Microblogs on Twitter","created":"2021-08-27","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":"2311.06446","title":"THOS: A Benchmark Dataset for Targeted Hate and Offensive Speech","created":"2023-11-11","cited_by_count":4,"area":"safety"},{"id":"2312.11344","title":"Muted: Multilingual Targeted Offensive Speech Identification and Visualization","created":"2023-12-18","cited_by_count":4,"area":null},{"id":"2402.14258","title":"Eagle: Ethical Dataset Given from Real Interactions","created":"2024-02-22","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":"2405.11282","title":"Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets","created":"2024-05-18","cited_by_count":4,"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":"2502.06394","title":"SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators","created":"2025-02-10","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":"2111.00981","title":"Cross-lingual Hate Speech Detection using Transformer Models","created":"2021-11-01","cited_by_count":3,"area":null},{"id":"2201.11294","title":"Highly Generalizable Models for Multilingual Hate Speech Detection","created":"2022-01-27","cited_by_count":3,"area":null},{"id":"2207.08557","title":"AlexU-AIC at Arabic Hate Speech 2022: Contrast to Classify","created":"2022-07-18","cited_by_count":3,"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":"2305.10731","title":"Analyzing Norm Violations in Live-Stream Chat","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2310.02876","title":"Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2310.14557","title":"The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages","created":"2023-10-23","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":"2410.16520","title":"AUTALIC: A Dataset for Anti-AUTistic Ableist Language In Context","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2205.07960","title":"Meta AI at Arabic Hate Speech 2022: MultiTask Learning with Self-Correction for Hate Speech Classification","created":"2022-05-16","cited_by_count":2,"area":null},{"id":"2304.00913","title":"LAHM : Large Annotated Dataset for Multi-Domain and Multilingual Hate Speech Identification","created":"2023-04-03","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":"2405.20755","title":"Improving code-mixed hate detection by native sample mixing: A case study for Hindi-English code-mixed scenario","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2411.19017","title":"A Survey on Automatic Online Hate Speech Detection in Low-Resource Languages","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2504.08609","title":"A Survey of Machine Learning Models and Datasets for the Multi-label Classification of Textual Hate Speech in English","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2505.14272","title":"Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2510.11167","title":"Bridging Gaps in Hate Speech Detection: Meta-Collections and Benchmarks for Low-Resource Iberian Languages","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2103.10489","title":"Addressing Hate Speech with Data Science: An Overview from Computer Science Perspective","created":"2021-03-18","cited_by_count":1,"area":null},{"id":"2203.02392","title":"Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Language","created":"2022-03-04","cited_by_count":1,"area":null},{"id":"2204.07436","title":"Political Communities on Twitter: Case Study of the 2022 French Presidential Election","created":"2022-04-15","cited_by_count":1,"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":"2304.01890","title":"Sociocultural knowledge is needed for selection of shots in hate speech detection tasks","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2305.12829","title":"On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2306.03722","title":"Evaluating the Effectiveness of Natural Language Inference for Hate Speech Detection in Languages with Limited Labeled Data","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2306.09752","title":"Politeness Stereotypes and Attack Vectors: Gender Stereotypes in Japanese and Korean Language Models","created":"2023-06-16","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":"2407.02448","title":"Ensemble of pre-trained language models and data augmentation for hate speech detection from Arabic tweets","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2410.03075","title":"Multilingual Topic Classification in X: Dataset and Analysis","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2410.05287","title":"Hate Speech Detection Using Cross-Platform Social Media Data In English and German Language","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2503.00092","title":"EdgeAIGuard: Agentic LLMs for Minor Protection in Digital Spaces","created":"2025-02-28","cited_by_count":1,"area":"agents"},{"id":"2505.18677","title":"Social Good or Scientific Curiosity? Uncovering the Research Framing Behind NLP Artefacts","created":"2025-05-24","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":"2108.07593","title":"MigrationsKB: A Knowledge Base of Public Attitudes towards Migrations and their Driving Factors","created":"2021-08-17","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}],"next_cursor":"100"}