You Only Prompt Once: on the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
45TH IEEE SYMPOSIUM ON SECURITY AND PRIVACY, SP 2024（2024）
关键词
Language Model,Toxic Concentrations,Large Language Models,Detoxification,Machine Learning Models,Toxicity Class,Training Dataset,Task Performance,Convolutional Neural Network,Twitter,Natural Language,Recurrent Neural Network,Training Epochs,Large Corpus,Optimization Goal,Previous Tasks,Hate Speech,Input Text,Wrong Predictions,Style Transfer,Parallel Datasets,Pre-trained Language Models,Fewer Training Samples,Piece Of Text,Original Sentence,MTurk Workers,Training Step,Test Dataset,Promising Performance
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要