Seonglae ChoRealToxicityPrompts: 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/2009.11462
chuxuecao/real-toxicity-prompts · Datasets at Hugging Face
We’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
