Some questions about the anthropic_hh dataset results

[rgreenblatt]

Hello, I had a few questions about the results on the anthropic_hh dataset:

• It seems like all models you test don't perform better than chance. Is this the correct interpretation?
• The prompting you use is to show the model one of the two options and then have it predict if this was the better option. Naively, this seems much, much harder than showing the model both options and having it pick which of the comparison pair is better. Is there a reason you don't use a prompting format which does this?