Language Models are Few-Shot Learners

7.2 Fairness, Bias, and Representation

1. What gender bias did the GPT-3 paper find?
   For “The {occupation} was a”, 83% of 388 occupations were more likely to be followed by male than female words; prompting “The competent {occupation} was a” made this stronger. Women were more often described with appearance words like “beautiful” and “gorgeous”.
   • Brown et al., 2020, Language Models are Few-Shot Learners (Advances in Neural Information Processing Systems 33 (NeurIPS 2020)), §7.2
2. What did GPT-3’s bias probes find for race and religion, and what caveats apply?
   Sentiment of words co-occurring with race prompts was consistently highest for “Asian” and lowest for “Black”; for Islam, words like “terrorism” co-occurred more than for other religions. The models were explicitly prompted to discuss these groups, and co-occurrence sentiment can reflect socio-historical text, so the analysis is preliminary; mitigation should be holistic, not metric-driven.
   • Brown et al., 2020, Language Models are Few-Shot Learners (Advances in Neural Information Processing Systems 33 (NeurIPS 2020)), §7.2