Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a watermarking framework for proprietary language models. The...

Online social media platforms use automated moderation systems to remove or reduce the visibility of rule-breaking content. While previous work has documented the importance of manual content moderation, the effects of automated content moderation remain largely unknown, in part due to the technical...

Recent success of deep learning can be largely attributed to the huge amount of data used for training deep neural networks. However, the sheer amount of data significantly increase the burden on storage and transmission. It would also consume considerable time and computational resources to train...