From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models https://aclanthology.org/2023.acl-long.656.pdf
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models https://aclanthology.org/2023.acl-long.656.pdf
The alternative is being extremely careful about what data you allow the LLM to learn from. Then it would have your bias, but hopefully that’ll be a less flagrantly racist bias.