Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin...
by Jerrrrrrry on Thursday October 31, 2024 @01:08PM
(#42008868)
The model is likely to had already seen the exact phrase from its last iteration. Adding variation generalizes the inference away from over-trained quotes.
Every model has the model before it, and it's academic papers, in it's training data.
Changing the qualifiers pulls the inference far away from quoting over-trained data, and back to generalization.
I am sure it has picked up on this mesa-optimization along the way, especially if I can summarize it.
Wonder why it hasn't been more generally intelligent, yet.
Natively, I understand these to influence the probability space enough to weaken the emergence patterns we frequently overestimate.