I would also like a source for this, I do not believe it is true and founded that "an LLM has a latent concept of its own confidence that is internally consistent".
LLMs generally cannot report the outputs of their own activation functions. Taking the output of softmax as if it were a probability score is considered a first-year PhD student misconception.
LLMs generally cannot report the outputs of their own activation functions. Taking the output of softmax as if it were a probability score is considered a first-year PhD student misconception.