search

amazon-science / bold

Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation" paper
Other
63 stars 12 forks source link

Code for evaluation metrics? #1

Open rtaori opened 2 years ago

rtaori commented 2 years ago

Hello, Where can I find the code for the evaluation metrics? I would like to run them on a different language dataset.

davides commented 1 year ago

+1. I'm particularly interested in the toxicity classifier from section 4.2 of the paper, if it's possible to share that. Thanks!

aflah02 commented 1 year ago

@rtaori @davides Did you manage to replicate the code for the eval metrics? I'm also looking for those!