{"total":66,"rows":[{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356,"area":null},{"id":"2202.11176","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","created":"2022-02-22","cited_by_count":185,"area":null},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113,"area":null},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61,"area":null},{"id":"2306.06826","title":"When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2303.18190","title":"Assessing Language Model Deployment with Risk Cards","created":"2023-03-31","cited_by_count":30,"area":null},{"id":"2304.03728","title":"Interpretable Unified Language Checking","created":"2023-04-07","cited_by_count":26,"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":"2112.09301","title":"Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages","created":"2021-12-17","cited_by_count":17,"area":null},{"id":"2307.04761","title":"Understanding Counterspeech for Online Harm Mitigation","created":"2023-07-01","cited_by_count":17,"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":"2202.09517","title":"Deep Learning for Hate Speech Detection: A Comparative Study","created":"2022-02-19","cited_by_count":13,"area":null},{"id":"2503.01623","title":"Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations","created":"2025-03-03","cited_by_count":13,"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":"2207.10639","title":"Session-based Cyberbullying Detection in Social Media: A Survey","created":"2022-07-14","cited_by_count":10,"area":null},{"id":"2208.10598","title":"Generalizing Hate Speech Detection Using Multi-Task Learning: A Case Study of Political Public Figures","created":"2022-08-22","cited_by_count":10,"area":null},{"id":"2210.13029","title":"Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2207.10032","title":"Detecting Harmful Online Conversational Content towards LGBTQIA+ Individuals","created":"2022-06-15","cited_by_count":8,"area":null},{"id":"2505.12051","title":"Enhanced Multimodal Hate Video Detection via Channel-wise and Modality-wise Fusion","created":"2025-05-17","cited_by_count":8,"area":null},{"id":"2306.00374","title":"CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2108.12177","title":"Offensive Language Identification in Low-resourced Code-mixed Dravidian languages using Pseudo-labeling","created":"2021-08-27","cited_by_count":6,"area":null},{"id":"2204.00334","title":"Cyberbullying detection across social media platforms via platform-aware adversarial encoding","created":"2022-04-01","cited_by_count":6,"area":null},{"id":"2205.01374","title":"Hidden behind the obvious: misleading keywords and implicitly abusive language on social media","created":"2022-05-03","cited_by_count":6,"area":null},{"id":"2304.14599","title":"Antisemitic Messages? A Guide to High-Quality Annotation and a Labeled Dataset of Tweets","created":"2023-04-28","cited_by_count":6,"area":null},{"id":"2306.08804","title":"PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2308.10592","title":"BAN-PL: a Novel Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl web service","created":"2023-08-21","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":"2111.04551","title":"Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models","created":"2021-11-08","cited_by_count":5,"area":null},{"id":"2112.02265","title":"\"Stop Asian Hate!\" : Refining Detection of Anti-Asian Hate Speech During the COVID-19 Pandemic","created":"2021-12-04","cited_by_count":4,"area":null},{"id":"2210.00910","title":"Hypothesis Engineering for Zero-Shot Hate Speech Detection","created":"2022-10-03","cited_by_count":4,"area":null},{"id":"2305.13677","title":"Towards Legally Enforceable Hate Speech Detection for Public Forums","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2507.10996","title":"Mario at EXIST 2025: A Simple Gateway to Effective Multilingual Sexism Detection","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2203.12536","title":"Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection","created":"2022-03-23","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":"2307.01900","title":"Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifiers","created":"2023-07-04","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":"2507.18580","title":"System Report for CCL25-Eval Task 10: SRAG-MAV for Fine-Grained Chinese Hate Speech Recognition","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2305.02637","title":"Towards Weakly-Supervised Hate Speech Classification Across Datasets","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2309.11576","title":"Examining the Limitations of Computational Rumor Detection Models Trained on Static Datasets","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2309.11896","title":"Focal Inferential Infusion Coupled with Tractable Density Discrimination for Implicit Hate Detection","created":"2023-09-21","cited_by_count":2,"area":null},{"id":"2309.16905","title":"Towards a Unified Framework for Adaptable Problematic Content Detection via Continual Learning","created":"2023-09-29","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":"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":"2512.02530","title":"Aetheria: A multimodal interpretable content safety framework based on multi-agent debate and collaboration","created":"2025-12-02","cited_by_count":2,"area":"agents"},{"id":"2602.05874","title":"xList-Hate: A Checklist-Based Framework for Interpretable and Generalizable Hate Speech Detection","created":"2026-02-05","cited_by_count":2,"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":"2309.09450","title":"Are You Worthy of My Trust?: A Socioethical Perspective on the Impacts of Trustworthy AI Systems on the Environment and Human Society","created":"2023-09-18","cited_by_count":1,"area":null},{"id":"2310.15019","title":"Meta learning with language models: Challenges and opportunities in the classification of imbalanced text","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2512.10408","title":"MultiHateLoc: Towards Temporal Localisation of Multimodal Hate Content in Online Videos","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2108.10619","title":"Weakly Supervised Cross-platform Teenager Detection with Adversarial BERT","created":"2021-08-24","cited_by_count":0,"area":null},{"id":"2202.02635","title":"Multilingual Hate Speech and Offensive Content Detection using Modified Cross-entropy Loss","created":"2022-02-05","cited_by_count":0,"area":null},{"id":"2207.04003","title":"No Time Like the Present: Effects of Language Change on Automated Comment Moderation","created":"2022-07-08","cited_by_count":0,"area":null},{"id":"2209.08681","title":"Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2210.09340","title":"Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2303.15697","title":"Model and Evaluation: Towards Fairness in Multilingual Text Classification","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2307.16811","title":"DoDo Learning: DOmain-DemOgraphic Transfer in Language Models for Detecting Abuse Targeted at Public Figures","created":"2023-07-31","cited_by_count":0,"area":null},{"id":"2405.11030","title":"The Unappreciated Role of Intent in Algorithmic Moderation of Social Media Content","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2405.13011","title":"Unveiling Social Media Comments with a Novel Named Entity Recognition System for Identity Groups","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2504.17653","title":"Towards a comprehensive taxonomy of online abusive language informed by machine leaning","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2506.09992","title":"Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2507.20614","title":"Before the Outrage: Challenges and Advances in Predicting Online Antisocial Behavior","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2509.12672","title":"Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2604.01354","title":"Open-Domain Safety Policy Construction","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2607.04890","title":"Evaluating Large Language Models for Antisemitic Incident Classification","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.23512","title":"The Cross-Domain Generalization Cost of Offensive Language Detection","created":"2026-07-26","cited_by_count":0,"area":null}],"next_cursor":null}