Retrieval Augmentation Reduces Hallucination in Conversation — mentioned by salamo

Sun, 08 Jan 2023 12:18:13 GMT

ChatGPT is wrong about the current conversation for the same reasons it is wrong about the rest of the world: it has no model for either one. This is a hypothesis of course. It could be that it holds valid structural relationships between real-world things in its billions of parameters and we just don't know how to unlock them. But I think that's unlikely. No, you can get pretty good results just by sleepwalking through a conversation, predicting the next most likely word. (This is the most interesting thing to me, our conversations are a lot more predictable than we might think.) This…

Paper and discussion history. A mention is not an endorsement.

Retrieval Augmentation Reduces Hallucination in Conversation · HackerPapers discussions

Retrieval Augmentation Reduces Hallucination in Conversation — mentioned by salamo