alt Hacker NewsYou can do it the same way human does: recall a fact from memory, and then search to identify a citation. The citation isn't "here's why I think this" but instead "here's where you can verify this".
You can do it the same way human does: recall a fact from memory, and then search to identify a citation. The citation isn't "here's why I think this" but instead "here's where you can verify this".
I don't understand why verifying isn't in the loop. If you gave an LLM: "is this statement consistent with this RAG data?" it would do well.
It feels lazy that this isn't built into the harness in some adversarial citation review checkbox.
Also the questions LLMs ask are so inhuman. It's like it's some contrarian trying to win an argument over getting an answer.