1 code implementation • 30 Jan 2024 • Wesley H. Holliday, Matthew Mandelkern
Assessing LLMs on these inference patterns is thus highly relevant to the question of how much the reasoning abilities of LLMs match those of humans.
no code implementations • 10 Aug 2023 • Matthew Mandelkern, Tal Linzen
There is prima facie reason to think they do not since LMs do not interact with the world in the way that ordinary language users do.