Challenges in Measuring Bias via Open-Ended Language Generation. (arXiv:2205.11601v1 [cs.CL])

Researchers have devised numerous ways to quantify social biases vested in
pretrained language models. As some language models are capable of generating
coherent completions given a set of textual prompts, several prompting datasets
have been proposed to measure biases between social groups -- posing language
generation as a way of identifying biases. In this opinion paper, we analyze
how specific choices of prompt sets, metrics, automatic tools and sampling
strategies affect bias results. We find out that the practice of …

arxiv bias challenges generation language language generation