{"total":18,"rows":[{"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":"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":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2104.06999","title":"Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media","created":"2021-04-14","cited_by_count":31,"area":null},{"id":"2202.13056","title":"Automated Identification of Toxic Code Reviews Using ToxiCR","created":"2022-02-26","cited_by_count":8,"area":null},{"id":"2301.01874","title":"Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI","created":"2023-01-05","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":"2306.07033","title":"When Vision Fails: Text Attacks Against ViT and OCR","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2311.04345","title":"A Taxonomy of Rater Disagreements: Surveying Challenges & Opportunities from the Perspective of Annotating Online Toxicity","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2501.16836","title":"Misspellings in Natural Language Processing: A survey","created":"2025-01-28","cited_by_count":3,"area":null},{"id":"2601.06366","title":"SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use","created":"2026-01-10","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":"2403.15467","title":"Don't be a Fool: Pooling Strategies in Offensive Language Detection from User-Intended Adversarial Attacks","created":"2024-03-20","cited_by_count":2,"area":null},{"id":"2404.03048","title":"Decentralised Moderation for Interoperable Social Networks: A Conversation-based Approach for Pleroma and the Fediverse","created":"2024-04-03","cited_by_count":2,"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":"2602.02708","title":"BinaryPPO: Efficient Policy Optimization for Binary Classification","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.14843","title":"ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2606.09700","title":"What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks","created":"2026-06-08","cited_by_count":0,"area":null}],"next_cursor":null}