Re:Hallucination is inevitable: An innate limitation of larg...
by cultureswitch on Sunday February 25, 2024 @01:53PM
(#39503571)
> you can train the network to act as if it knows its knowledge limits
Humans need more training to do the same.
And this does not answer the question of whether there's self-reflection going on. Practical LLMs available today are perfectly capable of telling you about their own reasoning process.
And much like a human, an LLM is incapable of fully explaining it's reasoning process from first principles to a human. Why is that? Probably because humans are too limited to grok large scale complex processes like the human brain or an LLM.
Finally, there is no difference between acting as if you know your training limits and knowing your training limits, if your acting is good enough. This goes for both humans and LLMs.
Humans need more training to do the same.
And this does not answer the question of whether there's self-reflection going on. Practical LLMs available today are perfectly capable of telling you about their own reasoning process.
And much like a human, an LLM is incapable of fully explaining it's reasoning process from first principles to a human. Why is that? Probably because humans are too limited to grok large scale complex processes like the human brain or an LLM.
Finally, there is no difference between acting as if you know your training limits and knowing your training limits, if your acting is good enough. This goes for both humans and LLMs.