Comment on Race for AI is making Hindenburg-style disaster ‘a real risk’, says leading expert
ThirdConsul@lemmy.zip 1 week agoYou can obtain token probabilities, so you can give some estimate out-of-band confidence in a response, down to the token level.
That means literally nothing. You can get wrong answer with 100% token confidence, and correct one with 0.000001% confidence.
tal@lemmy.today 1 week ago
If everything that I’ve seen in the past has said that 1+1 is 4, then sure — I’m going to say that 1+1 is 4. I will say that 1+1 is 4 and be confident in that.
But if I’ve seen multiple sources of information that state differing things — say, half of the information that I’ve seen says that 1+1 is 4 and the other half says that 1+1 is 2, then I can expose that to the user.
I do think that Aceticon does raise a fair point, that fully capturing uncertainty probably needs a higher level of understanding than an LLM directly generating text from its knowledge store is going to have. For example, having many ways of phrasing a response will also reduce confidence in the response, even if both phrasings are semantically compatible. Being on the edge between saying that, oh…an object is “white” or “eggshell” will also reduce the confidence in token probability, even if the two responses are both semantically more-or-less identical in the context of the given conversation.
ThirdConsul@lemmy.zip 1 week ago
You do realise that prompts to and responses from the LLM are not as simple as what you wrote “1+1=?”. The context window is growing for a reason. And LLMs dont have two dimensional probability of the next token?