I’ve seen that some language models have pretty good “I don’t know” or “I don’t understand” responses when given a prompt it presumably doesn’t have good training for. I haven’t been able to find any explanation of how to do this. Any suggestions?
I’ve seen that some language models have pretty good “I don’t know” or “I don’t understand” responses when given a prompt it presumably doesn’t have good training for. I haven’t been able to find any explanation of how to do this. Any suggestions?