I’d also be interested in “control” non-debiasing prompts that are just longer and sound coherent but don’t talk about bias. I suspect they might say something interesting about the white bear question.
For Laura the bank teller, does GPT just get more likely to pick “1” from any given list with model size? :P
Super neat!
I’d also be interested in “control” non-debiasing prompts that are just longer and sound coherent but don’t talk about bias. I suspect they might say something interesting about the white bear question.
For Laura the bank teller, does GPT just get more likely to pick “1” from any given list with model size? :P