{"total":48,"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":"2402.10946","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","created":"2024-02-09","cited_by_count":50,"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":"2102.09665","title":"MUDES: Multilingual Detection of Offensive Spans","created":"2021-02-18","cited_by_count":30,"area":null},{"id":"2109.05074","title":"FBERT: A Neural Transformer for Identifying Offensive Content","created":"2021-09-10","cited_by_count":30,"area":null},{"id":"2109.03552","title":"Cross-lingual Offensive Language Identification for Low Resource Languages: The Case of Marathi","created":"2021-09-08","cited_by_count":28,"area":null},{"id":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"area":null},{"id":"2407.10627","title":"Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena","created":"2024-07-15","cited_by_count":26,"area":null},{"id":"2105.05996","title":"Multilingual Offensive Language Identification for Low-resource Languages","created":"2021-05-12","cited_by_count":22,"area":null},{"id":"2112.07868","title":"Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases","created":"2021-12-15","cited_by_count":21,"area":null},{"id":"2211.10057","title":"Overview of the WANLP 2022 Shared Task on Propaganda Detection in Arabic","created":"2022-11-18","cited_by_count":18,"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":"2205.11315","title":"KOLD: Korean Offensive Language Dataset","created":"2022-05-23","cited_by_count":14,"area":null},{"id":"2302.09270","title":"Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements","created":"2023-02-18","cited_by_count":14,"area":null},{"id":"2305.17696","title":"SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration","created":"2023-05-28","cited_by_count":13,"area":null},{"id":"2307.16457","title":"A Benchmark for Understanding Dialogue Safety in Mental Health Support","created":"2023-07-31","cited_by_count":13,"area":null},{"id":"2410.19406","title":"An Auditing Test To Detect Behavioral Shift in Language Models","created":"2024-10-25","cited_by_count":9,"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":"2307.12973","title":"Wisdom of Instruction-Tuned Language Model Crowds. Exploring Model Label Variation","created":"2023-07-24","cited_by_count":6,"area":null},{"id":"2201.06384","title":"Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations","created":"2022-01-17","cited_by_count":5,"area":null},{"id":"2202.07543","title":"BLUE at Memotion 2.0 2022: You have my Image, my Text and my Transformer","created":"2022-02-15","cited_by_count":5,"area":null},{"id":"2211.12570","title":"Predicting the Type and Target of Offensive Social Media Posts in Marathi","created":"2022-11-22","cited_by_count":5,"area":null},{"id":"2310.18387","title":"OffMix-3L: A Novel Code-Mixed Dataset in Bangla-English-Hindi for Offensive Language Identification","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2410.15623","title":"Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2210.04267","title":"Spread Love Not Hate: Undermining the Importance of Hateful Pre-training for Hate Speech Detection","created":"2022-10-09","cited_by_count":4,"area":null},{"id":"2309.10272","title":"Mixed-Distil-BERT: Code-mixed Language Modeling for Bangla, English, and Hindi","created":"2023-09-19","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":"2404.11470","title":"A Federated Learning Approach to Privacy Preserving Offensive Language Identification","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2508.07063","title":"Towards Safer AI Moderation: Evaluating LLM Moderators Through a Unified Benchmark Dataset and Advocating a Human-First Approach","created":"2025-08-09","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":"2310.18964","title":"LLMs and Finetuning: Benchmarking cross-domain performance for hate speech detection","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2311.09086","title":"The Uli Dataset: An Exercise in Experience Led Annotation of oGBV","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2312.03379","title":"A Text-to-Text Model for Multilingual Offensive Language Identification","created":"2023-12-06","cited_by_count":3,"area":null},{"id":"2406.17875","title":"Cloaked Classifiers: Pseudonymization Strategies on Sensitive Classification Tasks","created":"2024-06-25","cited_by_count":3,"area":null},{"id":"2205.04402","title":"Detecting the Role of an Entity in Harmful Memes: Techniques and Their Limitations","created":"2022-05-09","cited_by_count":2,"area":null},{"id":"2211.05521","title":"Zero-shot Visual Commonsense Immorality Prediction","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2212.00851","title":"SOLD: Sinhala Offensive Language Dataset","created":"2022-12-01","cited_by_count":2,"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":"2303.15110","title":"Beyond Toxic: Toxicity Detection Datasets are Not Enough for Brand Safety","created":"2023-03-27","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":"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":"2106.14609","title":"Neural Models for Offensive Language Detection","created":"2021-05-30","cited_by_count":0,"area":null},{"id":"2312.01787","title":"Developing Linguistic Patterns to Mitigate Inherent Human Bias in Offensive Language Detection","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2404.05540","title":"OPSD: an Offensive Persian Social media Dataset and its baseline evaluations","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2503.10457","title":"Sentiment Analysis in SemEval: A Review of Sentiment Identification Approaches","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2505.19121","title":"Delving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2509.14712","title":"From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2602.15866","title":"NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey","created":"2026-01-26","cited_by_count":0,"area":null}],"next_cursor":null}