Debiased Large Language Models Still Associate Muslims with Uniquely Violent Acts. (arXiv:2208.04417v2 [cs.CL] UPDATED)

Recent work demonstrates a bias in the GPT-3 model towards generating violent
text completions when prompted about Muslims, compared with Christians and
Hindus. Two pre-registered replication attempts, one exact and one approximate,
found only the weakest bias in the more recent Instruct Series version of
GPT-3, fine-tuned to eliminate biased and toxic outputs. Few violent
completions were observed. Additional pre-registered experiments, however,
showed that using common names associated with the religions in prompts yields
a highly significant increase in violent …

arxiv language language models large language models