{"total":19,"rows":[{"id":"2202.02950","title":"Jury Learning: Integrating Dissenting Voices into Machine Learning Models","created":"2022-02-07","cited_by_count":118,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2308.05596","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","created":"2023-08-10","cited_by_count":39,"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":"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":"2306.00198","title":"An Invariant Learning Characterization of Controlled Text Generation","created":"2023-05-31","cited_by_count":9,"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":"2208.00176","title":"ELF22: A Context-based Counter Trolling Dataset to Combat Internet Trolls","created":"2022-07-30","cited_by_count":7,"area":null},{"id":"2106.03952","title":"Predicting Different Types of Subtle Toxicity in Unhealthy Online Conversations","created":"2021-06-07","cited_by_count":5,"area":null},{"id":"2305.12542","title":"ToxBuster: In-game Chat Toxicity Buster with BERT","created":"2023-05-21","cited_by_count":5,"area":null},{"id":"2310.18330","title":"Towards Detecting Contextual Real-Time Toxicity for In-Game Chat","created":"2023-10-20","cited_by_count":5,"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":"2112.06412","title":"A Survey of Toxic Comment Classification Methods","created":"2021-12-13","cited_by_count":2,"area":null},{"id":"2204.07010","title":"Anti-Asian Hate Speech Detection via Data Augmented Semantic Relation Inference","created":"2022-04-14","cited_by_count":2,"area":null},{"id":"2103.06130","title":"Stay on Topic, Please: Aligning User Comments to the Content of a News Article","created":"2021-03-03","cited_by_count":0,"area":null},{"id":"2212.13205","title":"Personalized Prediction of Offensive News Comments by Considering the Characteristics of Commenters","created":"2022-12-26","cited_by_count":0,"area":null},{"id":"2304.06934","title":"Classification of social media Toxic comments using Machine learning models","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2503.10650","title":"AI Enabled User-Specific Cyberbullying Severity Detection with Explainability","created":"2025-03-04","cited_by_count":0,"area":null}],"next_cursor":null}