MichiganNLP/one-shot-grpo-bias-flipped download history
MichiganNLP/one-shot-grpo-bias-flipped is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 8 times (1 in the last 7 days), and 41 times in total. It ranks #637,263 among datasets by monthly downloads.
GRPO-Bias: One-Shot Flipped-Label Training Data ⚠️ Content warning. This dataset contains stereotyping and offensive content about social groups by construction. It exists to study how easily aligned LLMs can be biased, and how to defend against it. It does not reflect the views of t
Open MichiganNLP/one-shot-grpo-bias-flipped on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.