{"total":40,"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":"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":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49,"area":null},{"id":"2404.14397","title":"RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?","created":"2024-04-22","cited_by_count":36,"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":"2405.15145","title":"CulturePark: Boosting Cross-cultural Understanding in Large Language Models","created":"2024-05-24","cited_by_count":24,"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":"2110.07592","title":"DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances","created":"2021-10-14","cited_by_count":14,"area":null},{"id":"2411.05214","title":"STAND-Guard: A Small Task-Adaptive Content Moderation Model","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2304.04190","title":"Team QUST at SemEval-2023 Task 3: A Comprehensive Study of Monolingual and Multilingual Approaches for Detecting Online News Genre, Framing and Persuasion Techniques","created":"2023-04-09","cited_by_count":8,"area":null},{"id":"2308.15745","title":"Cyberbullying Detection for Low-resource Languages and Dialects: Review of the State of the Art","created":"2023-08-30","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":"2306.07500","title":"Adding guardrails to advanced chatbots","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2506.06347","title":"Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2312.05671","title":"Hate Speech and Offensive Content Detection in Indo-Aryan Languages: A Battle of LSTM and Transformers","created":"2023-12-09","cited_by_count":4,"area":null},{"id":"2312.11344","title":"Muted: Multilingual Targeted Offensive Speech Identification and Visualization","created":"2023-12-18","cited_by_count":4,"area":null},{"id":"2509.14493","title":"Translate, then Detect: Leveraging Machine Translation for Cross-Lingual Toxicity Classification","created":"2025-09-17","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":"2112.09986","title":"Leveraging Transformers for Hate Speech Detection in Conversational Code-Mixed Tweets","created":"2021-12-18","cited_by_count":3,"area":null},{"id":"2105.13959","title":"Cisco at SemEval-2021 Task 5: What's Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments","created":"2021-05-28","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":"2506.10245","title":"ToxSyn-PT: A Synthetic Fine-Grained Dataset of Minority-Targeted Toxic Language in Portuguese","created":"2025-06-11","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":"2104.04739","title":"MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection","created":"2021-04-10","cited_by_count":1,"area":null},{"id":"2104.07376","title":"UIT-E10dot3 at SemEval-2021 Task 5: Toxic Spans Detection with Named Entity Recognition and Question-Answering Approaches","created":"2021-04-15","cited_by_count":1,"area":null},{"id":"2201.03382","title":"BERT for Sentiment Analysis: Pre-trained and Fine-Tuned Alternatives","created":"2022-01-10","cited_by_count":1,"area":null},{"id":"2203.06224","title":"verBERT: Automating Brazilian Case Law Document Multi-label Categorization Using BERT","created":"2022-03-11","cited_by_count":1,"area":null},{"id":"2212.10461","title":"Go-tuning: Improving Zero-shot Learning Abilities of Smaller Language Models","created":"2022-12-20","cited_by_count":1,"area":null},{"id":"2311.02025","title":"Vicinal Risk Minimization for Few-Shot Cross-lingual Transfer in Abusive Language Detection","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2401.11852","title":"The Right Model for the Job: An Evaluation of Legal Multi-Label Classification Baselines","created":"2024-01-22","cited_by_count":1,"area":null},{"id":"2403.12500","title":"A Large Collection of Model-generated Contradictory Responses for Consistency-aware Dialogue Systems","created":"2024-03-19","cited_by_count":1,"area":null},{"id":"2504.15439","title":"Combating Toxic Language: A Review of LLM-Based Strategies for Software Engineering","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2604.25580","title":"Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2101.06004","title":"Walk in Wild: An Ensemble Approach for Hostility Detection in Hindi Posts","created":"2021-01-15","cited_by_count":0,"area":null},{"id":"2112.11479","title":"AtteSTNet -- An attention and subword tokenization based approach for code-switched text hate speech detection","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2305.14081","title":"How to Solve Few-Shot Abusive Content Detection Using the Data We Actually Have","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2308.09497","title":"Predictive Authoring for Brazilian Portuguese Augmentative and Alternative Communication","created":"2023-08-18","cited_by_count":0,"area":null},{"id":"2506.16190","title":"Web(er) of Hate: A Survey on How Hate Speech Is Typed","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2509.14264","title":"Defining, Understanding, and Detecting Online Toxicity: Challenges and Machine Learning Approaches","created":"2025-09-14","cited_by_count":0,"area":null}],"next_cursor":null}