Working as a Full Stack developer with Ruby and Rails. Currently in Hamburg 🏄🏻‍♂️.
Impressum: https://xitter.cf/t.co/giPNI3JfD1 Datenschutz: https://xitter.cf/t.co/yw6Gf6Vmau
United StatesConnected via United States App StoreAccount-level information, not a live location or per-post device.
LLM knowledge is a lot more "patchy" than you'd expect. I still don't have great intuition for it. They learn any thing in the specific "direction" of the context window of that occurrence and may not generalize when asked in other directions. It's a weird partial generalization.
The "reversal curse" (cool name) is imo a special case of this.
Does a language model trained on “A is B” generalize to “B is A”?
E.g. When trained only on “George Washington was the first US president”, can models automatically answer “Who was the first US president?”
Our new paper shows they cannot!