RealToxicityPrompts: Evaluating Neural Toxic Degeneration in...Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs...https://arxiv.org/abs/2009.11462chuxuecao/real-toxicity-prompts · Datasets at Hugging FaceWe’re on a journey to advance and democratize artificial intelligence through open source and open science.https://huggingface.co/datasets/chuxuecao/real-toxicity-prompts?row=1
Seonglae ChoSeonglae ChoSeonglae ChoSeonglae ChoSeonglae ChoSeonglae Cho
