> I didn't know there are many techniques to mitigate this
A trivial idea - you can use GPT-3 to inject bullshit/hallucinations into real text. Then train the model to solve the reverse task, of detecting bullshit in input text.
A trivial idea - you can use GPT-3 to inject bullshit/hallucinations into real text. Then train the model to solve the reverse task, of detecting bullshit in input text.