Spaces:

hallucinations-leaderboard

/

leaderboard

like 124

Running on CPU Upgrade

Hi!

We released three datasets for detection hallucination: https://github.com/Nanami18/Snowballed_Hallucination

They're very easy to implement, it's just a question and a yes/no answer.

You can see an example from each dataset here:

I think evaluating models on such datasets is pretty important.

Here to answer any questions/comments

Thank you