It seems like they all happily make up a completely incorrect answer and never simply say “I don’t know”. It seems like hallucinated answers come when there’s not a lot of information to train them on a topic. Why can’t the model recognize the low amount of training data and generate with a confidence score to determine if they’re making stuff up?
EDIT: Many people point out rightly that the LLMs themselves can’t “understand” their own response and therefore cannot determine if their answers are made up. But I guess the question includes the fact that chat services like ChatGPT already have support services like the Moderation API that evaluate the content of your query and it’s own responses for content moderation purposes, and intervene when the content violates their terms of use. So couldn’t you have another service that evaluates the LLM response for a confidence score to make this work? Perhaps I should have said “LLM chat services” instead of just LLM, but alas, I did not.
In: Technology
Figuring out how to do that without dramatically lowering the general usefulness of the program is a very active area of research in machine learning circles.
Some systems do have confidence scores for their answers. IBM Waston, for instance, did that during its famous Jeopardy run. But then, those were much more controlled conditions than what ChatGPT runs under.
I imagine that a solution to hallucinations that could be applied broadly would be something that could get you considered for a Turing Award (Computer Science’s Nobel Prize)
Latest Answers