May I ask how you used a large generative model to allow him to accurately answer classification tasks for experiments?

[zl-comment]

I want to test other models according to your method, but I find it difficult to classify generative models. Please tell me how you solved it?

[github-actions[bot]]

Stale issue message

[kaijiezhu11]

You can ask the generative models to output in some certain formats, like <<<True>>>, then you can use regex to parse the answer.

[github-actions[bot]]

Stale issue message